Automated check-in of trucks at shipping and receiving facilities

Abstract

A system for automated check-in and routing of trucks at a shipping facility includes a queue camera capturing images of the facility entry area and a lane camera capturing images of vehicles within the entry area. A computing device receives a first video stream from the queue camera and detects a truck approaching a gate. Upon detecting the truck near the gate, the computing device receives a second video stream from the lane camera, detects an identifier for the truck, and matches the identifier to an order number. When the identifier is matched to the order number, the system transmits a destination to the truck driver, facilitating efficient check-in and routing within the shipping facility.

Description

AUTOMATED CHECK-IN OF TRUCKS AT SHIPPING AND RECEIVING FACILITIESCROSS REFERENCE TO RELATED APPLICATIONS

[0001] This application claims priority to U.S. Application No. 63 / 665,746, titled "Automated Check-in of Trucks at Shipping and Receiving Facilities," filed June 28, 2024, which is hereby incorporated by reference in its entirety.BACKGROUND

[0002] Embodiments, examples, and aspects relate to, among other things, automated systems for managing vehicle traffic at shipping and receiving facilities, and more particularly to a system for automatically identifying and routing trucks using computer vision and artificial intelligence.SUMMARY

[0003] Trucks (e.g., tractor-trailers, straight trucks, box trucks, and the like) are used to haul cargo of all sorts over the road. Cargo may be picked up or dropped off at various facilities (e.g., logistics centers, ports, warehouse terminals, freight yards, hubs, and the like). When a truck arrives at a facility to pick up an order, it must wait in a line and manually check in at a gate. The check-in process includes a driver of the truck engaging with a shipping agent to provide invoice and identification information. Once checked in, the truck is manually directed to its destination within the facility to pick up its order. Likewise, a truck that is delivering cargo to a facility must check in with a bill of lading and other information to be directed to a dock or other unloading point.

[0004] This check-in process can result in shipping delays, inaccurate information, inaccurate routing, and increased costs. For example, a truck may arrive at a facility and enter the queue, but its arrival is not recorded until it checks in at the gate. This time discrepancy results in mismatched records, which can lead to increased shipping costs. In addition, because the facility is not aware of the arrival, tasks such as preparing goods for loading, assigning loading docks, etc., which could otherwise be performed before the truck arrives at the gate, may be delayed. Similarly, late trucks may result in the reservation of docks that could otherwise be used for trucks that have arrived on time or early.

[0005] Automated systems for managing vehicle check-in and routing at shipping and logistics facilities have been developed to improve operational efficiency and reduce manual processing. Early approaches often relied on manual entry or barcode scanning at entry points,requiring drivers or personnel to present physical documents or identification tags for verification. While these methods provided a basic level of automation, they were limited by the need for human intervention and were prone to delays during peak traffic periods.

[0006] More recent systems have incorporated video surveillance and image recognition technologies to identify vehicles and streamline entry procedures. For example, some implementations use a single camera positioned at the facility gate to capture images of incoming trucks, combined with optical character recognition (OCR) to read license plates or container numbers. These systems typically focus on detecting vehicles at a single point and matching identifiers to pre-registered orders or manifests. However, such single-point detection can be challenged by occlusions, varying lighting conditions, and the need to process multiple vehicles simultaneously.

[0007] Other approaches have employed multiple cameras positioned at different locations within the entry area to track vehicle movement and improve identification accuracy. These systems may use one camera to monitor the queue of trucks waiting to enter and another to capture detailed images closer to the gate for identifier recognition. The data from these cameras is processed to detect vehicles, extract identifiers, and associate them with shipment orders. While these multi-camera setups enhance detection reliability and provide more comprehensive monitoring, integration of the video streams and real-time routing instructions to drivers remains complex and is often limited in scope.

[0008] These previous approaches have utilized manual input, single-point imaging, or multi-camera monitoring to facilitate truck check-in and routing at shipping facilities. However, none of these approaches have provided a comprehensive solution that combines the features described in this disclosure.

[0009] To address, among other things, these problems, systems and methods are provided here for automatically checking in and routing trucks as they arrive at a shipping and receiving facility. Among other things, embodiments provided herein use cameras and artificial intelligence methods to automatically identify and track trucks as they arrive at the facility. Using embodiments presented herein, trucks can be identified and matched with their corresponding shipments using video of the truck in a queue lane and data provided by the truck’s driver during an electronic pre-check process. Using such embodiments, a truck arriving at the gate is completing, not beginning, the check in process. It can immediately proceed to its assigned dock for loading or unloading. This results in more efficient use of equipment, improved shipping times, and reduced costs. In addition, the embodiments presented herein reduce human error by reducing human involvement in the check in process.

[0010] In some aspects, the techniques described herein relate to a system for automated check-in and routing of trucks at a shipping facility, including: a queue camera positioned to capture images of a facility entry area; a lane camera positioned to capture images of vehicles within the facility entry area; and a computing device configured to: receive a first video stream from the queue camera; detect a first truck in the first video stream; determine when the first truck is approaching a gate of the facility entry area; responsive to determining that the first truck is approaching the gate: receive a second video stream from the lane camera; detect an identifier for the first truck in the second video stream; match the identifier to an order number; and responsive to matching the identifier to the order number, transmit a destination to a driver of the first truck.

[0011] In some aspects, the techniques described herein relate to a method for automated check-in and routing of trucks at a shipping facility, including: receiving a first video stream from a queue camera positioned to capture images of a facility entry area; detecting a first truck in the first video stream; determining when the first truck is approaching a gate of the facility entry area; responsive to determining that the first truck is approaching the gate: receiving a second video stream from a lane camera positioned to capture images of vehicles within the facility entry area; detecting an identifier for the first truck in the second video stream; matching the identifier to an order number; and responsive to matching the identifier to the order number, transmitting a destination to a driver of the first truck.

[0012] In some aspects, the techniques described herein relate to a non-transitory computer- readable medium storing instructions that, when executed by a processor, cause the processor to perform operations for automated check-in and routing of trucks at a shipping facility, the operations including: receiving a first video stream from a queue camera positioned to capture images of a facility entry area; detecting a first truck in the first video stream; determining when the first truck is approaching a gate of the facility entry area; responsive to determining that the first truck is approaching the gate: receiving a second video stream from a lane camera positioned to capture images of vehicles within the facility entry area; detecting an identifier for the first truck in the second video stream; matching the identifier to an order number; and responsive to matching the identifier to the order number, transmitting a destination to a driver of the first truck.BRIEF DESCRIPTION OF THE SEVERAL VIEWS OF THE DRAWINGS

[0013] In the accompanying figures similar or the same reference numerals may be repeated to indicate corresponding or analogous elements. These figures, together with the detailed description, below are incorporated in and form part of the specification and serve to furtherillustrate various embodiments of concepts that include the claimed invention, and to explain various principles and advantages of those embodiments.

[0014] FIG. 1 is a block diagram illustrating one example of a system for automated truck check in, in accordance with some embodiments.

[0015] FIG. 2 illustrates a flow chart of a method implemented by the system of FIG. 1, in accordance with some embodiments.

[0016] FIGS 3A and 3B illustrate graphical user interfaces used in the operation of the method of FIG. 2, in accordance with some embodiments.

[0017] FIG. 4 illustrates a flow chart of a method implemented by the system of FIG. 1, in accordance with some embodiments.

[0018] FIG. 5 illustrates aspects of the operation of the method of FIG. 4, in accordance with some embodiments.

[0019] FIG. 6 illustrates aspects of the operation of the method of FIG. 4, in accordance with some embodiments.

[0020] FIG. 7 illustrates a graphical user interface used in the operation of the method of FIG. 2, in accordance with some embodiments.

[0021] FIG. 8 illustrates a flowchart of a method for processing image data from multiple lanes at a facility, according to aspects of the present disclosure.

[0022] FIG. 9 illustrates a flowchart of a distributed model training method across multiple facilities, according to an embodiment.

[0023] FIG. 10 illustrates a block diagram of a data processing and integration system for truck check-in operations, according to aspects of the present disclosure.

[0024] FIG. 11 illustrates a graphical user interface for displaying and managing truck check-in information, according to an embodiment.

[0025] FIG. 12 illustrates another example of the graphical user interface including an image review screen, according to aspects of the present disclosure.

[0026] FIG. 13 illustrates a flowchart of an example state machine method for an automated check-in process, according to an embodiment.

[0027] FIG. 14 illustrates a block diagram of a computer vision processing system, according to aspects of the present disclosure.

[0028] Skilled artisans will appreciate that elements in the figures are illustrated forsimplicity and clarity and have not necessarily been drawn to scale. For example, the dimensions of some of the elements in the figures may be exaggerated relative to other elements to help improve understanding of embodiments of the present disclosure.

[0029] The system, apparatus, and method components have been represented where appropriate by conventional symbols in the drawings, showing only those specific details that are pertinent to understanding the embodiments of the present disclosure so as not to obscure the disclosure with details that will be readily apparent to those of ordinary skill in the art having the benefit of the description herein.DETAILED DESCRIPTION

[0030] Before any embodiments of the invention are explained in detail, it is to be understood that the invention is not limited in its application to the details of construction and the arrangement of components set forth in the following description or illustrated in the following drawings. The invention is capable of other embodiments and of being practiced or of being carried out in various ways.

[0031] Advantages and features consistent with this disclosure are set forth in the following detailed description, with reference to the figures.

[0032] For ease of description, some or all of the example systems presented herein are illustrated with a single exemplar of each of its component parts. Some examples may not describe or illustrate all components of the systems. Other embodiments may include more or fewer of each of the illustrated components, may combine some components, or may include additional or alternative components.

[0033] FIG. 1 illustrates an example system 100 for automatically identifying and tracking arriving trucks at a facility. The system 100 includes a queue camera 102, one or more lane cameras 104, a computing device 106, and a database 108. As illustrated in FIG. 1, the queue camera 102, the lane cameras 104, the computing device 106, and other components may be coupled via a communications network 110. The communications network 110 may include wireless and wired components and may be implemented using various local and wide area networks, for example, a Bluetooth™ network, a Wi-Fi™ network), the Internet, a land mobile radio network, a cellular data network, a Long Term Evolution (LTE) network, a 4G network, a 5G network, or combinations or derivatives thereof.

[0034] The computing device 106 and the database 108 operate to, among other things, automatically detect and identify trucks using images received from the queue camera 102 and the lane cameras 104, as described herein. The computing device 106 includes one or moreelectronic processors (for example, a microprocessor, or other electronic controller), an electronic memory, a network interface, and other various modules coupled directly, by one or more control or data buses, or combinations thereof. The memory may include read-only memory, random access memory, other non-transitory computer-readable media, or combinations thereof. In one example, the one or more electronic processors of the computing device 106 configured to retrieve instructions and data from the memory and execute, for example, functions as described herein. The computing device 106 is communicatively coupled to, and writes data to and from, the database 108.

[0035] In the illustrated embodiment, the database 108 is a database housed on a suitable database server communicatively coupled to and accessible by the computing device 106. In some instances, the database 108 is part of a cloud-based database system external to the system 100 and accessible by the computing device 106 over one or more wired or wireless networks. In other instances, all or part of the database 108 is locally stored on the computing device 106. In some instances, both the computing device 106 and the database 108 may be part of a cloudbased system. In some examples, the system 100 may be configured and controlled via a computer console, which is communicatively coupled to the computing device 106. In the illustrated example, the database 108 includes machine learning models for analyzing images received from the queue camera 102 and the lane cameras 104, truck and driver data, and shipping data, as described herein.

[0036] In some instances, the computing device 106 performs machine learning functions, for example, to detect and classify objects within images received from the queue camera 102 and the lane cameras 104. Machine learning generally refers to the ability of a computer program to leam without being explicitly programmed. In some instances, a computer program (e.g., a learning engine) is configured to construct an algorithm based on inputs. Supervised learning involves presenting a computer program with example inputs and their desired outputs. The computer program is configured to learn a general rule that maps the inputs to the outputs from the training data it receives. Example machine learning engines include decision tree learning, association rule learning, artificial neural networks, classifiers, inductive logic programming, support vector machines, clustering, Bayesian networks, reinforcement learning, representation learning, similarity and metric learning, sparse dictionary learning, and genetic algorithms. Using all of these approaches, a computer program can ingest, parse, and understand data, and progressively refine algorithms for data analytics. In some instances, the machine learning functions described herein may be distributed among combinations of the computing device 106, the queue camera 102, and the lane cameras 104. For example, the queue camera 102 may include machine learning engines for detecting trucks in the queue lanes and may send thatinformation to the computing device 106. In another example, the lane cameras 104 may include machine learning engines for identifying specific trucks, as described herein.

[0037] In the example illustrated, the queue camera 102 and the lane cameras 104 are electronic cameras, which contain image capture devices for capturing images and video streams by, for example, sensing light in at least the visible spectrum. It should be noted that the terms “image” and “images,” as used herein, may refer to one or more digital images captured by the queue camera 102 and / or the lane cameras 104, or processed by the computing device 106. Further, the terms “image” and “images,” as used herein, may refer to still images or sequences of images (e.g., a video streamer video clip).

[0038] In the example illustrated, the queue camera 102 and the lane cameras 104 are positioned to capture a portion of or the entire facility entry area 112. The facility entry area 112 controls entry of trucks into the facility. In the illustrated example, the facility entry area 112 includes three lanes, each terminating in one of a plurality of gates 114. In some embodiments, the gates may be controlled by the computing device 106, as described herein. As the trucks 116 arrive at the facility, they queue up in the lanes of the facility entry area 112. In some instances, a facility entry area 112 may have more or fewer than three lanes.

[0039] The queue camera 102 is positioned to capture images of most or all of the facility entry area 112. The queue camera 102 is in an elevated position relative to the lane cameras 104. As described herein, images from the queue camera 102 are used to identify and track the trucks 116 as they enter and move through their respective lanes.

[0040] The lane cameras 104 are positioned to capture images of individual trucks 116 as they move through their respective lanes. The lane cameras 104 may be positioned nearer to the ground than the queue camera 102. As an example, the system 100 is illustrated having two lane cameras 104. In practice, the number of lane cameras 104 may vary, depending on the configuration of the facility and the facility entry area 112. In some configurations (e.g., a single lane), one lane cameras 104 may be sufficient. In other configurations, more than two lane cameras 104 may be needed. In some instances, there may be one or more lane cameras 104 assigned for each lane.

[0041] In some instances, the configuration of the facility and the facility entry area may allow for a single camera to serve as both the queue and lane camera.

[0042] A driver arriving at the facility entry area 112 uses a driver device 118 (e.g., a smart telephone or other portable electronic device) to provide check-in data (e.g., an id number for the driver’s truck, an order number for the load being picked up, etc.) to the computing device.

[0043] Pre-check information may also be received from a carrier database, a dispatcher device, or another suitable means A carrier database, for example, may be maintained by a trucking company. These databases typically contain detailed records of shipment schedules, truck locations, and driver assignments. Similarly, pre-check information can be obtained from dispatcher devices, whether they are operated by local dispatchers in a yard or by remote dispatchers managing a fleet. An example of a local dispatcher device could be a yard management system used by a warehouse to coordinate truck arrivals and departures, while a remote dispatcher might use a fleet management system like those provided by Omnitracs or Samsara.

[0044] As described below, the computing device 106 analyzes images from the queue camera 102 and the lane cameras 104 to identify and track the truck, matching the check-in data with the truck and directing it the appropriate dock (e.g., based on shipping data stored in the database 108). In some instances, driver device 118, the computing device 106, or both, communicate with a remote logistics system 120.

[0045] FIG. 2 is a flowchart illustrating a method 200 for automated check in and routing of trucks, according to some examples. The method 200 may be modified or performed differently than the specific example provided. As an example, the method 200 is described as being performed by the system 100.

[0046] The method 200 begins with a driver submitting a pre-check form. This submission may take place prior to arrival at a facility (e.g., at block 201), or may take place as a truck arrives at the facility to drop off or pick up a shipment. For example, at block 202, a driver may scan (e.g., with a smart phone) a QR code, which provides a link to a web-based application. The web-based application may be hosted in the logistics system 120 or in a cloud-based application instance. In some instances, access verification is required prior to accessing the pre-check form in the application.

[0047] At block 204, the driver initiates a verification process. In one example, the driver submits a phone number (e.g., for the phone requesting access to the web-based application) to request a verification code via SMS. In another example, the driver submits an order number (e.g., corresponding to one or more of the products the driver has arrived to drop off or pick up at the facility).

[0048] At block 206, verification is performed. For example, the verification code received via SMS may be entered in the web-based application and confirmed valid. In another example, a submitted order number may be checked against a list of valid orders. In some instances, the order number may be linked to other data (e.g., a phone number, an arrival window, etc.), whichmay be used in conjunction with the order number to verify the driver. In some aspects, IP -based or other rate limiting techniques are used to prevent order numbers from being used to verify incorrect drivers.

[0049] Upon verification, (at block 206), the driver is presented with the pre-check form. FIG. 3A is a screenshot 300 of an example SMS-based validation exchange.

[0050] FIG. 3B illustrates an example graphical user interface 302, presenting a pre-check form. In the illustrated example, a driver submits an order type (e.g., a live load or a preload), their name, a mobile phone number (e.g., for receiving SMS messages), a pickup or delivery number (e.g., provided by the shipper or receiver of the goods), and a trailer number. In some embodiments, the form may allow drivers to submit additional information (e.g., a destination for the order, a carrier name, and the like). In aspects, the interface may provide user interface elements (e.g., a drop down list), from which a user may select one of multiple potential values. In some instances, other information may be requested. For example, as illustrated in FIG. 3B, a trailer type and size may be requested. In another example, FIG. 7 shows a graphical user interface 700, which allows a driver to submit information about the truck’s trailer type. In some instances, this information may be used to more quickly identify the truck, as described below.

[0051] Returning to FIG. 2, at block 210, a pre-check validation is performed. For example, the application compares the data provided to shipping data (e.g., in the database 108 or the remote logistics system 120) to locate a matching order at the facility. When the pre-check cannot be validated (at block 214), the central shipping office (CSO) for the facility may contact the driver for more information (at block 216). For example, the web-based application may include a chat function, a call may be placed to the phone number used to request access to the pre-check form, or an SMS message may be sent to the driver. The CSO works with the driver to acquire addition information, or correct the originally provided information, to validate the precheck. In some instances, validation may include verifying the truck’s location at the facility (e.g., by sharing a GPS location from the smart phone via the web-based application).

[0052] Whether additional information is necessary or the pre-check information is sufficient (at block 212), the driver is pre-checked (at block 218) when matched to an order (e.g., an order to pick up goods from or deliver goods to the facility).

[0053] At block 220, the truck is captured by the computing device 106, the queue camera 102, and one or more lane cameras 104. When the truck is identified by number at a gate, the driver is checked in automatically (at block 222). An example method 400 for capturing and identifying the truck is set forth below with respect to FIGS. 4-6. In some instances, when the automated check in completes, (at block 224) the driver receives an SMS message indicating adestination within the facility (e.g., a dock door). An example SMS message is illustrated in FIG. 3A. In some instances, other forms of electronic communication may be used, such as a message to a dedicated software application.

[0054] In some instances, the computing device 106, when check-in is complete, controls the applicable gate 114 to open, allowing the truck to enter and proceed to the assigned dock (at block 226).

[0055] In some instances, SMS communication may be used to provide other information to the driver. For example, the driver can be sent facility rules, indications that their order is not ready, indications of loading or unloading status, and the like.

[0056] In some instances, the information on the pre-check form may be known by the system 100 ahead of time. For example, a carrier may provide information on trucks and orders to the system 100 via a software API. Using the known information matching DOT numbers and trailer numbers to orders check in could be performed automatically at the gate, as described above, without the need for pre-check.

[0057] In some instances, an AI / ML powered chatbot or other interface may be provided to collect driver information and communicate with the driver via text message. The chatbot may be an alternative check-in channel to the web-based application. In some aspects, the chatbot may provide user interactions with the CSO (Centralized Shipping Office). Such a chatbot may be implemented locally to the facility (e.g., on the computing device 106), remotely (e.g., in a cloud-based computing instance), or by using a combination of both.

[0058] FIG. 4 is a flowchart illustrating a method 400 for automated check in and routing of trucks, according to some examples. The method 400 may be modified or performed differently than the specific example provided. As an example, the method 400 is described as being performed by the system 100, in particular the computing device 106, the queue camera 102, and the lane cameras 104. Portions of FIG. 4 illustrate physical components of the system 100 and other portions of FIG. 4 illustrate logical representations of steps performed in hardware, software, or combinations of both. The steps described may be performed by the computing device 106, the queue camera 102, the lane cameras 104, or combinations thereof.

[0059] In some aspects, the method 400 is performed continuously, as video streams are received and processed. For example a video stream 402 (from the queue camera 102) is received and analyzed using machine learning models trained to detect and classify trucks. As illustrated in FIG. 4, the detection and classification may take place in the queue camera 102. However, it should be understood that the detection and classification of the queue camera video stream 402 may take place in the computing device 106.

[0060] At block 404, truck detection is performed. For example, as illustrated in FIG.5, a truck 502 is shown in a bounding box 506 and a truck 504 is shown in a bounding box 508. In some examples, the machine learning model used to detect the trucks is trained with a curated annotated dataset containing tens of thousands of images of trucks likely to arrive at the facility.

[0061] As trucks are identified, they are assigned an identifier, which is stored in the database 108. The assigned identifier is used to identify and track the truck locally.

[0062] At block 406, the trucks identified (at block 404) are assigned lane identifiers based on the lane they are in. For example, the computing device 106 may analyze the video including the detected trucks to determine lanes for the identified trucks. These lane identifiers are stored in the database 108 (at block 410).

[0063] In some instances, other information is associated with and stored with the truck identifier and lane identifier (e.g., a time stamp indicating when the truck was detected, a position of the truck in the lane (e.g., 2ndin line), etc.).

[0064] As the video stream 402 is received and analyzed, the computing device 106 tracks the location of the trucks (identified at block 404) as they move through the queue until a truck arrives at its gate (at 412). When a truck arrives at its gate (i.e., the gate for the lane in which the truck is traveling), a video stream 414 from the associated lane cameras 104 is analyzed to match the truck with pre-check information (collected as described above with respect to FIG. 2). This is done by looking for unique identifiers on the truck itself, which may have been provided during pre-check. Examples include numeric or alphanumeric identifiers, such as aUS Department of Transportation (DOT) number and a trailer number. In some instances, trucks may also be identified using non-alphanumeric identifiers, for example, QR codes, bar codes, logos, and other graphical identifiers.

[0065] At block 416, bounding box detection is performed as illustrated, for example, in FIG. 6. FIG. 6 illustrates an image 600 of a truck 602, received from a lane camera 104. In some instances, bounding box detection is performed using machine learning models trained using annotated images including examples of DOT numbers and trailer numbers in a variety of locations and styles. In FIG. 6, the machine learning model has detected a trailer number in bounding box 604 and a DOT number in bounding box 606.

[0066] Returning to FIG. 4, the bounding box image is saved (at block 418) remotely, for example in the logistics system 120. The images may also be saved locally in the database 108. In some instances, the saved images may be attached to records for the shipping transaction, providing a proof of pickup or delivery. In some instances, the saved images are used to further train the machine learning models.

[0067] At block 420, optical character recognition is performed on the portions of the images within the bounding boxes (detected at block 416). The detected text is stored in the database 108 (at block 422). At block 424, if the text is incomplete, the computing device 106 (or the lane cameras 104) continues to analyze the image looking for DOT numbers or trailer numbers. Text may be considered incomplete if the format does not match a pre-determined format for DOT or trailer numbers. It may also be considered incomplete if the optical character recognition was incomplete (e.g., something was in the way of the number, vibration or movement blurred the image, or some other reason).

[0068] When text recognition is complete, the data is used to complete check in (as described in the method 200). In some instances, the data may be presented on a dashboard 428 of an application (e.g., a part of the remote logistics system 120) used by the CSO. Additional data may also be collected and stored (e.g., a time stamp indicating when the truck arrived at the gate).

[0069] In some examples, the system 100 is used to track an inventory of trucks at the facility. For example, as trucks are pre-checked and checked in, the database 108 is populated with data describing the trucks present at the facility. Data on a truck may include timestamps for the truck’s arrival in queue and at the gate, lane number of entry, DOT number, trailer number, trailer size, order / delivery number, dock number, driver name, driver phone number, and the like. In some examples, the system 100 may include cameras positioned at an exit of the facility to automatically identify trucks as they leave and mark their status in the database as departed.

[0070] FIG. 8 illustrates a flowchart of a method 800 for processing image data from multiple lanes at a facility. The method 800 shows parallel processing paths for three lanes, with each lane operating independently while following similar processing steps.

[0071] The method 800 begins with the video stream 402 feeding into the block 404 for truck detection. This is followed by the block 406 for finding the lane, which has three possible paths labeled 1, 2, and 3 corresponding to different lanes. In some cases, a QueueView component may manage the workflow, ensuring that text is only read from new subjects, thereby optimizing processing efficiency.

[0072] For each lane, the process includes a store text step 802 and a store id step 804. These steps feed into a pattern matching step 806. The pattern matching software stack may capture each datapoint, potentially reducing redundancy of overlapping sensors. After pattern matching, the process moves to the block 412 labeled "Truck at Gate?".

[0073] If a truck is detected at the gate (Yes branch), the process proceeds to acquire images through the video stream 414. The acquired images undergo character recognition at the block420. During this step, each lane may independently identify when text is obstructed, allowing for adaptive processing. If no truck is detected (No branch), the process continues monitoring.

[0074] Following character recognition, the process moves to the block 424 "Is Text Complete?". If the text is not complete (No branch), the process loops back to acquire more images. If the text is complete (Yes branch), the process moves to an output text step 808.

[0075] The method 800 processes data from the queue camera 102 and the lane cameras 104, with the processed information ultimately flowing to the logistics system 120. In some implementations, the Cloud-based logistics system 120 may cache information to allow for timeseries classifications, potentially enhancing the system's ability to track and analyze truck movements over time.

[0076] The flowchart shows how the system handles multiple lanes simultaneously while maintaining separate processing paths for each lane's data. This parallel structure demonstrates how the system processes information from three lanes concurrently, with each lane following the same sequence of detection, pattern matching, character recognition, and text output steps. This approach may allow for efficient processing of multiple trucks entering the facility simultaneously.

[0077] In some cases, the method 800 may operate using only the lane cameras 104 without relying on the queue camera 102 for tracking. This configuration may allow for flexibility in facility layouts where a queue camera 102 is not practical or necessary.

[0078] The store text step 802 and store id step 804 may involve saving detected information to the database 108. This stored information may be used for later verification or analysis. The pattern matching step 806 may compare detected information against known patterns or expected formats for truck identifiers.

[0079] The output text step 808 may involve sending the processed information to other systems, such as the logistics system 120, for further action or record-keeping. This step may facilitate the automated check-in process by providing verified truck identification data to relevant facility systems. The caching of information by the Cloud-based logistics system 120 may enable more sophisticated analysis and classification of truck movements and patterns over time.

[0080] It should be understood that, for DOT numbers and Trailer numbers, a 100% match is not required for the detected numbers to be used. For example, known carriers DOT numbers are stored, as described herein. In some instances, readings close to known DOT numbers aregrouped with them. In another example, a trailer number may be an 80% match with a record and may not match with any other records. In such cases, the 80% match may be deemed a full match.

[0081] FIG. 9 illustrates a flowchart of a method 900 for distributed model training across multiple facilities. The method 900 shows parallel processing paths for six facilities, with each facility having similar processing components and data flows.

[0082] The method 900 includes truck scanning facilities 904, 906, 908, 910, 912, and 914. At block 916, a truck is scanned, with images processed as described previously. Following the truck scanning, each facility's process flow includes an "Is Edge Case?" decision point, represented by block 918 for facility 904 and similar decision points for other facilities.

[0083] When the "Is Edge Case?" evaluation returns "No," the process continues scanning for trucks at block 916. When the evaluation returns "Yes," the process stores the image in the cloud-based logistics system 120. This system utilizes images from all facilities to update the model. At block 920, the updated model is received by facility 904 and deployed to improve truck scanning.

[0084] The facilities are interconnected through the cloud-based logistics system 120, facilitating data sharing. This interconnection allows for online learning, enabling the model to improve with each truck entering any facility. This continuous learning process may reduce edge case conditions and improve overall system accuracy across all facilities.

[0085] The cloud-based logistics system 120 allows edge cases captured at one facility to enhance model predictions across all facilities. This shared learning approach may accelerate the system's ability to handle diverse and challenging scenarios, potentially improving the robustness of the truck identification and tracking process.

[0086] The method 900 may generate substantial amounts of data, potentially hundreds of terabytes per month for each facility. By combining processing power and storage in the cloud, the system can save salient images across all locations and constantly update model weights. This approach may help reduce storage requirements while maintaining or improving model performance.

[0087] At block 922, the cloud-based logistics system 120 aggregates data from all connected facilities, analyzes patterns, and generates updated models. These updated models are then distributed back to the individual facilities, creating a continuous improvement cycle for the truck identification and tracking system.

[0088] The method 900 may utilize the queue camera 102 and lane cameras 104 at each facility to capture images for processing. The computing device 106 at each facility may perform initial processing before sending relevant data to the cloud-based logistics system 120.

[0089] In some implementations, the database 108 at each facility may store local copies of machine learning models, periodically updated with improved versions from the cloud-based logistics system 120. This approach may allow for continued operation even during temporary network disruptions.

[0090] The communications network 110 plays a crucial role in the method 900, facilitating efficient exchange of large volumes of image data and model updates between individual facilities and the cloud-based logistics system 120.

[0091] The driver device 118 may be integrated into the method 900, providing additional data points for model training. For example, driver check-in information collected through the graphical user interface 700 may be correlated with image data to improve truck identification accuracy.

[0092] The pattern matching step 806 from method 800 may be enhanced by this distributed model training approach. As more diverse data is collected and processed across multiple facilities, the pattern matching algorithms may become more robust and adaptable to various truck configurations and identification markings.

[0093] The store text step 802 and store id step 804 from method 800 may feed into the edge case detection process of method 900. Unusual or difficult-to-classify data identified during these steps may be flagged for further analysis in the cloud-based system, contributing to the ongoing improvement of the model across all facilities.

[0094] FIG. 10 illustrates a block diagram of a data processing and integration system for truck check-in operations. The system shows the flow of data between multiple components including cameras, databases, user interfaces, and processing modules.

[0095] The system includes a Queue View camera and a Lane camera that capture image data. The captured data flows through initial processing steps where timestamp, lane number, and truck position information may be recorded. This information may be stored in corresponding database tables.

[0096] The system incorporates an Azure SQL database component that may combine data from multiple sources. The database may perform matching operations based on timestamp and lane number information. The combined data may include truck identification details, timestamps, and trailer information.

[0097] A driver app / chatbot interface may collect driver information including driver name, phone number, delivery number, and trailer details. This information may flow to a Pre Check component which may process the data and trigger gate operations.

[0098] The system includes multiple data combination steps where information from different sources may be merged. The process may involve matching records based on trailer numbers and USDOT identifiers. The final combined records may include comprehensive data from driver pre-check and camera detection systems.

[0099] In some cases, the system may utilize database tables with detailed field listings showing the specific data points collected and processed at each stage. The system may culminate in gate operation controls and check-in verification processes.

[0100] The data flow paths between components may be indicated with arrows showing the direction of information transfer. This structure may allow for efficient integration of data from various sources, potentially enabling a more streamlined check-in process for trucks entering the facility.

[0101] In some cases, the system may incorporate real-time data processing capabilities, allowing for immediate updates to the check-in status as new information becomes available from either the cameras or the driver interface. This approach may help reduce wait times and improve overall efficiency of the check-in process.

[0102] The system may also include error handling and data validation steps to ensure the accuracy and reliability of the information being processed. These measures may help prevent issues such as mismatched truck identifications or incorrect gate assignments.

[0103] In some implementations, the system may provide interfaces for manual override or correction of automated decisions, allowing facility staff to intervene if necessary. This feature may add flexibility to the system and help address unusual or complex situations that may arise during the check-in process.

[0104] The data processing and integration system may be designed with scalability in mind, potentially allowing for the addition of new data sources or processing modules as the needs of the facility evolve. This modular approach may facilitate future upgrades or expansions to the system's capabilities.

[0105] FIG. 11 illustrates a graphical user interface 1100 for displaying and managing truck check-in information. The graphical user interface 1100 may include a record 1102 containing multiple columns for organizing truck-related data.

[0106] The graphical user interface 1100 may display several data columns including a truck id column 1104, a check-in time column 1106, a lane id column 1108, a dot number column 1110, a trailer number column 1112, and a tracking duration column 1114. Each column may present specific information about trucks entering the facility entry area.

[0107] In some cases, the truck id column 1104 may contain unique identifiers assigned to each truck by the computing device. The check-in time column 1106 may display timestamps indicating when each truck was detected at the gate. The lane id column 1108 may show numerical identifiers corresponding to the specific lane a truck used to enter the facility.

[0108] The dot number column 1110 may contain Department of Transportation (DOT) numbers detected from the trucks by the lane cameras. Similarly, the trailer number column 1112 may display trailer numbers identified from the video streams. The tracking duration column 1114 may show the amount of time each truck was tracked within the facility entry area.

[0109] The graphical user interface 1100 may include record sorting controls 1116 that allow for organization of the displayed information. A search interface 1118 may enable users to search through the data. The interface may show DOT numbers 1119 and trailer numbers 1120 associated with vehicles.

[0110] In some cases, the graphical user interface 1100 may include functionality for handling a binned DOT number 1122, which may indicate when a DOT number matches a known carrier in the database. The interface may present information in rows, with each row containing data about a specific truck's check-in event.[0U1] The graphical user interface 1100 may serve as a dashboard for monitoring system performance across multiple facilities. In some cases, the data displayed in the graphical user interface 1100 may be aggregated from various facilities and updated in real-time through the communications network.

[0112] The search interface 1118 may allow users to filter and locate specific truck records based on various criteria such as DOT numbers, trailer numbers, or check-in times. This functionality may enable efficient management of truck traffic and quick resolution of any discrepancies in the check-in process.

[0113] In some cases, the record sorting controls 1116 may allow users to organize the displayed information based on any of the columns, facilitating analysis of truck flow patterns or identification of potential bottlenecks in the check-in process.

[0114] The graphical user interface 1100 may be accessible through the computing device or remotely via the logistics system, allowing authorized personnel to monitor and manage truck check-in operations from various locations.

[0115] FIG. 12 illustrates an image display 1200 of the graphical user interface 1100. The image display 1200 may include a recording window 1202 and verification controls 1204.

[0116] The recording window 1202 may display captured footage of a truck in a facility lane. In some cases, the recording window 1202 may show identification markings on the truck, such as DOT numbers and trailer numbers. The footage displayed in the recording window 1202 may be captured by the lane cameras 104 as trucks approach the facility entry area 112.

[0117] The verification controls 1204 may allow users to confirm or reject detected identification numbers. In some cases, the verification controls 1204 may display confidence scores for different possible matches of DOT numbers and trailer numbers detected from the images. These confidence scores may be generated by the computing device 106 based on the analysis of the video streams from the lane cameras 104.

[0118] The image display 1200 may enable users to review detected truck information and verify identification accuracy. Users may interact with the verification controls 1204 to confirm or correct the automated detections made by the system. This verification process may serve as part of a verification engine to validate detections and potentially improve model accuracy over time.

[0119] In some cases, the image display 1200 may allow users to review multiple lane entries through a single consolidated view. The recording window 1202 may provide visual confirmation of truck identification data alongside the automated detection results, allowing for efficient verification of the system's performance.

[0120] The graphical user interface 1100, including the image display 1200, may serve as a Niagara Eye UI for development and verification purposes. This interface may allow system operators or developers to monitor the performance of the automated check-in system, verify detections, and potentially identify areas for improvement in the truck identification process.

[0121] In some cases, the verified information from the image display 1200 may be stored in the database 108 or transmitted to the logistics system 120 via the communications network 110. This verified data may be used to update and refine the machine learning models used for truck detection and identification, potentially improving the system's accuracy over time.

[0122] FIG. 13 illustrates a flowchart of a method 1300 for an automated check-in state machine process. The method 1300 includes multiple states and processing steps organized into two main operational sections: a running state 1302 and an active learning state 1304.

[0123] The method 1300 may begin with a ready state 1306, which may transition into the running state 1302. Within the running state 1302, the process may flow through several steps, beginning with a tracking step 1308 that may feed into a decoding step 1310. The decoding step 1310 may connect to a verify step 1312, which in turn may connect to a sending step 1314. The sending step 1314 may loop back to the tracking step 1308, potentially creating a continuous processing cycle within the running state 1302.

[0124] In some cases, the tracking step 1308 may involve processing video streams from the queue camera and the lane cameras to identify and track trucks within the facility entry area. The decoding step 1310 may involve optical character recognition to extract DOT numbers and trailer numbers from the captured images.

[0125] The verify step 1312 may compare the extracted information against pre-check data stored in the database. The sending step 1314 may transmit verified truck information to the logistics system or the driver device.

[0126] The decoding step 1310 may also connect to the active learning state 1304, which may contain its own sequence of steps. Within the active learning state 1304, the process may move through a scoring step 1316 to an uploading step 1318. From the uploading step 1318, the flow may continue to a training step 1320, followed by a testing step 1322, and may conclude with a deploy step 1324.

[0127] In some cases, the scoring step 1316 may evaluate the confidence levels of the decoded information. The uploading step 1318 may send high-confidence data to the cloudbased logistics system for further processing. The training step 1320 may use the uploaded data to refine the machine learning models used in the decoding process.

[0128] The testing step 1322 may evaluate the performance of the updated models, while the deploy step 1324 may implement the improved models back into the running state 1302.

[0129] The method 1300 may include an error state 1326 that may be triggered from the running state 1302. The error state 1326 may represent a condition where the normal processing flow may be interrupted, potentially due to issues such as camera malfunctions or network connectivity problems.

[0130] In some cases, the computing device may manage the transitions between the running state 1302 and the active learning state 1304. The communications network mayfacilitate the exchange of data between the local system components and the cloud-based logistics system during the active learning process.

[0131] The graphical user interface may provide visual feedback on the current state of the method 1300, potentially allowing system operators to monitor the automated check-in process and intervene if necessary.

[0132] The method 1300 may demonstrate the interconnected nature of the processing steps, with data potentially flowing between the running state 1302 and active learning state 1304. The process may maintain separate paths for active operation and learning functions while allowing for error handling through the error state 1326.

[0133] FIG. 14 illustrates a computer vision processing system 1400 for automated truck check-in and identification. The computer vision processing system 1400 may include a neural core module 1402, a verification engine 1404, a long short-term memory module 1406, and a flask page 1408.

[0134] The neural core module 1402 may process image data from the queue camera 102 and the lane cameras 104. In some cases, the neural core module 1402 may include an object detection module 1410, a re-identification tracker module 1412, and an OCR module 1414.

[0135] The object detection module 1410 may contain an object detection model 1416 and an object tracker 1418. In some cases, the object detection model 1416 may be a lightweight model specialized for detecting trucks and identifiers. The object tracker 1418 may track detected trucks across multiple frames.

[0136] The OCR module 1414 may include an OCR module 1420 and a region of interest crop module 1422. The region of interest crop module 1422 may extract specific areas of the image for text recognition. In some cases, the OCR module 1414 may use different bounding box orientations (horizontal, vertical, diagonal) to improve accuracy.

[0137] The re-identification tracker module 1412 may contain a Bounding box Intersection over Union threshold 1424, a cosine similarity module 1426, and an object association module 1428. These components may work together to maintain consistent tracking of trucks across different camera views.

[0138] The verification engine 1404 may include a reward function module 1430 and a data manager 1432. The reward function module 1430 may contain a reward calculator 1434 and a long short-term memory monitor 1436. These components may evaluate the performance of the detection and tracking processes.

[0139] The data manager 1432 may include DOT number binning 1438 and a storage transfer module 1440. In some cases, the DOT number binning 1438 may categorize known DOT numbers to improve matching accuracy. The storage transfer module 1440 may manage data transfer between different system components.

[0140] In some aspects, the DOT number binning 1438 may implement a technique for enhancing DOT number recognition. This technique may involve maintaining a database of known carriers and their associated DOT numbers. When processing images, if a detected DOT number matches one in this database of known carriers, the system may automatically assign it a high confidence score.

[0141] For example, in some implementations, if the system detects DOT number 0080806 and recognizes this as belonging to a well-known carrier, it may automatically associate this detection with that carrier and assign it a high confidence score. This binning process may allow for more accurate and efficient DOT number matching, particularly for frequently encountered carriers.

[0142] The binning approach may improve overall system accuracy by leveraging prior knowledge about common carriers. It may reduce false positives and increase confidence in correct detections for known carriers, while still allowing flexibility to detect and process DOT numbers from less frequent or unknown carriers.

[0143] In some cases, the storage transfer module 1440 may work in conjunction with the DOT number binning 1438 to efficiently manage and transfer binned DOT number data between different components of the system. This may include transferring updated binning information to image processing modules, verification engines, or other system components that may benefit from the enhanced DOT number recognition capabilities.

[0144] The data manager 1432 may also include functionality to periodically update and refine the database of known carriers and their DOT numbers. This may involve processes for adding new carriers, removing outdated information, or adjusting confidence scores based on historical detection accuracy. By maintaining an up-to-date and accurate binning database, the system may continuously improve its DOT number recognition capabilities over time.

[0145] A data connector 1442 may link the verification engine 1404 to other system components. The long short-term memory module 1406 may store truck records 1444 and include a SQL database 1446. The SQL database 1446 may contain verified DOT numbers 1448 and check-in attempt history 1450.

[0146] The flask page 1408 may include a flask web page 1452 with several components: check in attempts 1454, a machine learning sandbox 1456, a camera positioning aid 1458, and a 3D simulation module 1460. These components may provide user interface and development tools for the system.

[0147] In some cases, the computing device 106 may use a weighted scoring system to evaluate detected identifiers. This scoring system may consider factors such as detection confidence, OCR accuracy, and consistency across multiple frames. For example, a DOT number detected with 95% confidence in three consecutive frames may receive a higher score than one detected with 80% confidence in a single frame. The system may assign different weights to various identifier types, giving higher priority to DOT numbers (weight factor of 0.6) over trailer numbers (weight factor of 0.4) when both are detected. Additionally, the scoring system may incorporate contextual factors such as lighting conditions, with detections made under optimal lighting receiving a confidence multiplier of 1.2 compared to those made in poor lighting conditions. The system may also evaluate character-level confidence, where a DOT number with all digits detected above 90% confidence receives a higher overall score than one where some digits have lower confidence values. These weighted scores help determine when an identifier is considered sufficiently reliable for matching with pre-check information in the database 108.

[0148] The computer vision processing system 1400 may communicate with other system components through the communications network 110. The processed and verified information may be sent to the logistics system 120 for further action, such as gate control and driver notification.

[0149] As should be apparent from this detailed description above, the operations and functions of the electronic computing device are sufficiently complex as to require their implementation on a computer system, and cannot be performed, as a practical matter, in the human mind. Electronic computing devices such as set forth herein are understood as requiring and providing speed and accuracy and complexity management that are not obtainable by human mental steps, in addition to the inherently digital nature of such operations (e.g., a human mind cannot interface directly with RAM or other digital storage, cannot transmit or receive electronic messages, electronically encoded video, electronically encoded audio, etc., and cannot process multiple video streams simultaneously to detect and track vehicles in real-time, among other features and functions set forth herein).

[0150] In the foregoing specification, specific embodiments are described. However, one of ordinary skill in the art appreciates that various modifications and changes may be made without departing from the scope of the invention as set forth in the claims below. Accordingly, thespecification and figures are to be regarded in an illustrative rather than a restrictive sense, and all such modifications are intended to be included within the scope of present teachings.

[0151] In the foregoing specification, specific embodiments have been described. However, one of ordinary skill in the art appreciates that various modifications and changes can be made without departing from the scope of the invention as set forth in the claims below. Accordingly, the specification and figures are to be regarded in an illustrative rather than a restrictive sense, and all such modifications are intended to be included within the scope of present teachings. The benefits, advantages, solutions to problems, and any element(s) that may cause any benefit, advantage, or solution to occur or become more pronounced are not to be construed as a critical, required, or essential features or elements of any or all the claims. The invention is defined solely by the appended claims including any amendments made during the pendency of this application and all equivalents of those claims as issued.

[0152] Moreover, in this document, relational terms such as first and second, top and bottom, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. The terms “comprises,” “comprising,” “has,” “having,” “includes,” “including,” “contains,” “containing,” or any other variation thereof, are intended to cover a nonexclusive inclusion, such that a process, method, article, or apparatus that comprises, has, includes, contains a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by “comprises .. . a,” “has .. . a,” “includes .. . a,” or “contains ... a” does not, without more constraints, preclude the existence of additional identical elements in the process, method, article, or apparatus that comprises, has, includes, contains the element. Unless the context of their usage unambiguously indicates otherwise, the articles “a,” “an,” and “the” should not be interpreted as meaning “one” or “only one.” Rather these articles should be interpreted as meaning “at least one” or “one or more.” Likewise, when the terms “the” or “said” are used to refer to a noun previously introduced by the indefinite article “a” or “an,” “the” and “said” mean “at least one” or “one or more” unless the usage unambiguously indicates otherwise.

[0153] Also, it should be understood that the illustrated components, unless explicitly described to the contrary, may be combined or divided into separate software, firmware, and / or hardware. For example, instead of being located within and performed by a single electronic processor, logic and processing described herein may be distributed among multiple electronic processors. Similarly, one or more memory modules and communication channels or networks may be used even if embodiments described or illustrated herein have a single such device or element. Also, regardless of how they are combined or divided, hardware and softwarecomponents may be located on the same computing device or may be distributed among multiple different devices. Accordingly, in this description and in the claims, if an apparatus, method, or system is claimed, for example, as including a controller, control unit, electronic processor, computing device, logic element, module, memory module, communication channel or network, or other element configured in a certain manner, for example, to perform multiple functions, the claim or claim element should be interpreted as meaning one or more of such elements where any one of the one or more elements is configured as claimed, for example, to make any one or more of the recited multiple functions, such that the one or more elements, as a set, perform the multiple functions collectively.

[0154] Example embodiments are herein described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems) and computer program products according to example embodiments. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a special purpose and unique machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. The methods and processes set forth herein need not, in some embodiments, be performed in the exact sequence as shown and likewise various blocks may be performed in parallel rather than in sequence. Accordingly, the elements of methods and processes are referred to herein as “blocks” rather than “steps.”

[0155] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function / act specified in the flowchart and / or block diagram block or blocks.

[0156] The computer program instructions may also be loaded onto a computer or other programmable data processing apparatus that may be on or off-premises, or may be accessed via the cloud in any of a software as a service (SaaS), platform as a service (PaaS), or infrastructure as a service (laaS) architecture so as to cause a series of operational blocks to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide blocks for implementing the functions / acts specified in the flowchart and / or block diagram blockor blocks. It is contemplated that any part of any aspect or embodiment discussed in this specification can be implemented or combined with any part of any other aspect or embodiment discussed in this specification.

[0157] It will be appreciated that some embodiments may be comprised of one or more generic or specialized processors (or “processing devices”) such as microprocessors, digital signal processors, customized processors and field programmable gate arrays (FPGAs) and unique stored program instructions (including both software and firmware) that control the one or more processors to implement, in conjunction with certain non-processor circuits, some, most, or all of the functions of the method and / or apparatus described herein. Alternatively, some or all functions could be implemented by a state machine that has no stored program instructions, or in one or more application specific integrated circuits (ASICs), in which each function or some combinations of certain of the functions are implemented as custom logic. Of course, a combination of the two approaches could be used.

[0158] Moreover, an embodiment can be implemented as a computer-readable storage medium having computer readable code stored thereon for programming a computer (e.g., comprising a processor) to perform a method as described and claimed herein. Any suitable computer-usable or computer readable medium may be utilized. Examples of such computer- readable storage mediums include, but are not limited to, a hard disk, a CD-ROM, an optical storage device, a magnetic storage device, a ROM (Read Only Memory), a PROM (Programmable Read Only Memory), an EPROM (Erasable Programmable Read Only Memory), an EEPROM (Electrically Erasable Programmable Read Only Memory) and a Flash memory. In the context of this document, a computer-usable or computer-readable medium may be any medium that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.

[0159] Further, it is expected that one of ordinary skill, notwithstanding possibly significant effort and many design choices motivated by, for example, available time, current technology, and economic considerations, when guided by the concepts and principles disclosed herein will be readily capable of generating such software instructions and programs and ICs with minimal experimentation. For example, computer program code for carrying out operations of various example embodiments may be written in an object oriented programming language such as Rust, Go, Java, Smalltalk, C++, Python, or the like. However, the computer program code for carrying out operations of various example embodiments may also be written in conventional procedural programming languages, such as the “C” programming language or similar programming languages. The program code may execute entirely on a computer, partly on the computer, as a stand-alone software package, partly on the computer and partly on a remote computer or serveror entirely on the remote computer or server. In the latter scenario, the remote computer or server may be connected to the computer through a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0160] The terms “substantially,” “essentially,” “approximately,” “about,” or any other version thereof, are defined as being close to as understood by one of ordinary skill in the art, and in one non-limiting embodiment the term is defined to be within 10%, in another embodiment within 5%, in another embodiment within 1% and in another embodiment within 0.5%. The term “one of,” without a more limiting modifier such as “only one of,” and when applied herein to two or more subsequently defined options such as “one of A and B” should be construed to mean an existence of any one of the options in the list alone (e.g., A alone or B alone) or any combination of two or more of the options in the list (e.g., A and B together).

[0161] A device or structure that is “configured” in a certain way is configured in at least that way but may also be configured in ways that are not listed.

[0162] The terms “coupled,” “coupling,” or “connected” as used herein can have several different meanings depending on the context in which these terms are used. For example, the terms coupled, coupling, or connected can have a mechanical or electrical connotation. For example, as used herein, the terms coupled, coupling, or connected can indicate that two elements or devices are directly connected to one another or connected to one another through intermediate elements or devices via an electrical element, electrical signal or a mechanical element depending on the particular context.

[0163] The Abstract of the Disclosure is provided to allow the reader to quickly ascertain the nature of the technical disclosure. It is submitted with the understanding that it will not be used to interpret or limit the scope or meaning of the claims. In addition, in the foregoing Detailed Description, it can be seen that various features are grouped together in various embodiments for the purpose of streamlining the disclosure. This method of disclosure is not to be interpreted as reflecting an intention that the claimed embodiments require more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive subject matter lies in less than all features of a single disclosed embodiment. Thus, the following claims are hereby incorporated into the Detailed Description, with each claim standing on its own as a separately claimed subject matter.

[0164] Various features and advantages of the embodiments and examples presented herein are set forth in the following claims.

Claims

CLAIMSWhat is claimed is:

1. A system for automated check-in and routing of trucks at a shipping facility, comprising: a queue camera positioned to capture images of a facility entry area; a lane camera positioned to capture images of vehicles within the facility entry area; and a computing device configured to: receive a first video stream from the queue camera; detect a first truck in the first video stream; determine when the first truck is approaching a gate of the facility entry area; responsive to determining that the first truck is approaching the gate: receive a second video stream from the lane camera; detect an identifier for the first truck in the second video stream; match the identifier to an order number; and responsive to matching the identifier to the order number, transmit a destination to a driver of the first truck.

2. The system of claim 1, wherein the computing device is further configured to: receive pre-check information associated with the first truck prior to the first truck arriving at the facility entry area; and use the pre-check information to match the identifier to the order number.

3. The system of claim 1, wherein receiving pre-check information associated with the first truck includes receiving pre-check information from at least one selected from the group consisting of a driver device, a carrier database, and a dispatcher device.

4. The system of claim 2, wherein the pre-check information includes at least one of: a driver name, a mobile phone number, a pickup or delivery number, or a trailer number.

5. The system of claim 1, wherein the identifier for the first truck includes at least one of: a Department of Transportation (DOT) number, a trailer number, a QR code, a bar code, or a logo.

6. The system of claim 1, wherein the computing device is further configured to: detect a second truck in the first video stream; determine a lane assignment for the second truck; and store the lane assignment in a database.

7. The system of claim 6, wherein the computing device is further configured to: track the second truck as it moves through the facility entry area using the first video stream; and update the lane assignment in the database as the second truck changes lanes.

8. The system of claim 1, wherein transmitting the destination to the driver of the first truck comprises sending an SMS message to a mobile device associated with the driver.

9. A method for automated check-in and routing of trucks at a shipping facility, comprising: receiving a first video stream from a queue camera positioned to capture images of a facility entry area; detecting a first truck in the first video stream; determining when the first truck is approaching a gate of the facility entry area; responsive to determining that the first truck is approaching the gate: receiving a second video stream from a lane camera positioned to capture images of vehicles within the facility entry area; detecting an identifier for the first truck in the second video stream; matching the identifier to an order number; and responsive to matching the identifier to the order number, transmitting a destination to a driver of the first truck.

10. The method of claim 9, further comprising: receiving pre-check information from a driver device associated with the first truck prior to the first truck arriving at the facility entry area; and using the pre-check information to match the identifier to the order number.

11. The method of claim 10, wherein the pre-check information includes at least one of: a driver name, a mobile phone number, a pickup or delivery number, or a trailer number.

12. The method of claim 9, wherein the identifier for the first truck includes at least one of: a Department of Transportation (DOT) number, a trailer number, a QR code, a bar code, or a logo.

13. The method of claim 9, further comprising: detecting a second truck in the first video stream; determining a lane assignment for the second truck; and storing the lane assignment in a database.

14. The method of claim 13, further comprising: tracking the second truck as it moves through the facility entry area using the first video stream; and updating the lane assignment in the database as the second truck changes lanes.

15. The method of claim 9, wherein transmitting the destination to the driver of the first truck comprises sending an SMS message to a mobile device associated with the driver.

16. A non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to perform operations for automated check-in and routing of trucks at a shipping facility, the operations comprising: receiving a first video stream from a queue camera positioned to capture images of a facility entry area;detecting a first truck in the first video stream; determining when the first truck is approaching a gate of the facility entry area; responsive to determining that the first truck is approaching the gate: receiving a second video stream from a lane camera positioned to capture images of vehicles within the facility entry area; detecting an identifier for the first truck in the second video stream; matching the identifier to an order number; and responsive to matching the identifier to the order number, transmitting a destination to a driver of the first truck.

17. The non-transitory computer-readable medium of claim 16, wherein the operations further comprise: receiving pre-check information from a driver device associated with the first truck prior to the first truck arriving at the facility entry area; and using the pre-check information to match the identifier to the order number.

18. The non-transitory computer-readable medium of claim 17, wherein the pre-check information includes at least one of: a driver name, a mobile phone number, a pickup or delivery number, or a trailer number.

19. The non-transitory computer-readable medium of claim 16, wherein the identifier for the first truck includes at least one of: a Department of Transportation (DOT) number, a trailer number, a QR code, a bar code, or a logo.

20. The non-transitory computer-readable medium of claim 16, wherein the operations further comprise: detecting a second truck in the first video stream; determining a lane assignment for the second truck; and storing the lane assignment in a database.

21. The non-transitory computer-readable medium of claim 20, wherein the operations further comprise: tracking the second truck as it moves through the facility entry area using the first video stream; and updating the lane assignment in the database as the second truck changes lanes.

Images