System and method for determining occupancy in a region of interest

Abstract

Method for determining occupancy in a region of interest (ROI), comprising: obtaining an image of the ROI 401; generating a heat map of the ROI from the image; determining from the heat map of the ROI

Description

TECHNICAL FIELD

[0001] The present disclosure generally relates to detection of occupancy in a region of interest. In particular, the present disclosure relates to a means to accurately detect a number of occupants in a region of interest. BACKGROUND

[0002] Background description includes information that may be useful in understanding the present invention. It is not an admission that any of the information provided herein is prior art or relevant to the presently claimed invention, or that any publication specifically or implicitly referenced is prior art.

[0003] In many vehicles, autonomous systems, such as air conditioning, audio-visual systems, safety systems, advanced driver-assist systems (ADAS), etc. operate based on a number of occupants in a cabin of the vehicle. The systems are customized to provide optimum driving conditions and comfort to the passengers. In order to enable optimal operation, it is important to accurately determine occupancy in the vehicle. However, conventional means to determine occupancy are often inadequate as they may not be able to accurately detect occupancy if any of the occupants are in any convoluted poses.

[0004] Patent document US20210402942 provides systems and methods that accurately identify driver and passenger in-cabin activities that may indicate a biomechanical distraction that prevents a driver from being fully engaged in driving a vehicle. In particular, image data representative of an image of an occupant of a vehicle may be applied to one or more deep neural networks (DNNs). Using the DNNs, data indicative of key point locations corresponding to the occupant may be computed, a shape and / or a volume corresponding to the occupant may be reconstructed, a position and size of the occupant may be estimated, hand gesture activities may be classified, and / or body postures or poses may be classified. These determinations may be used to determine operations or settings for the vehicle to increase not only the safety of the occupants, but also of surrounding motorists, bicyclists, and pedestrians.

[0005] Patent document US10657396 provides a method for detecting passenger statuses by analyzing a 2D interior image of a vehicle is provided. The method includes steps of: a passenger status-detecting device (a) inputting the 2D interior image taken with a fisheye lens into a pose estimation network to acquire pose points corresponding to passengers; and (b) (i) calculating location information on the pose points relative to a preset reference point by referring to a predetermined pixel-angle table, if a grid board has been placed in the vehicle, the pixel-angle table has been created such that vertical angles and horizontal angles, formed by a first line and second lines, correspond to pixels of grid comers, in which the first line connects a camera and a top center of the grid board and the second lines connects the comers and the camera and (ii) detecting the passenger statuses by referring to the location information.

[0006] However, the cited patent documents do not provide an adequate solution for accurately determining occupancy in a vehicle.

[0007] There is, therefore, a requirement in the art for a means to accurately and effectively determine an occupancy in a vehicle. OBJECTS OF INVENTION

[0008] An object of the present invention is to provide a system and a method for determining an occupancy in a region of interest.

[0009] Another object of the present invention is to provide a system for accurately determining presence of one or more occupants in a region of interest irrespective of a pose adopted by the one or more occupants.

[0010] Another object of the present invention is to provide a system for limiting false positives and false negatives of occupancy in the ROI.

[0011] Another object of the present invention is to provide a system having a structure correction mechanism to counter any misprediction of joints from the pose estimation neural network. SUMMARY

[0012] The present disclosure generally relates to detection of occupancy in a region of interest. In particular, the present disclosure relates to a means to accurately detect a number of occupants in a region of interest.

[0013] In a first aspect, the present disclosure provides a system for determining occupancy in a region of interest (ROI). The system includes a computing device including a processor and a memory communicably coupled to the processor, the memory storing instructions executable by the processor. The computing device is configured to receive, from one or more visual sensors disposed in the ROI, one or more visual images of the ROI. The computing device is further configured to generate, from the one or more images, a heat map of the ROI. The computing device is further configured to determine, from the heat map of the RO I, a first set of attributes indicative of presence of one or more potential occupants in the ROI. The first set of attributes is based on pose attributes of the one or more potential occupants. The computing device is further configured to determine, from the heat map of the ROI and the first set of attributes, a second set of attributes indicative of presence of the one or more potential occupants in the ROI. The second set of attributes is based on skeletal attributes of the one or more potential occupants in the ROI. The computing device is further configured to determine, based on any one or both of the first and second attributes, an estimated pose of the one or more potential occupants in the ROI. The computing device is configured to determine the occupancy in the ROI based on a number of distinct estimated poses determined.

[0014] In some embodiments, the pose attributes include a plurality of possible poses of the one or more potential occupants in the ROI.

[0015] In some embodiments, the skeletal attributes include relative location and identity of any one or a combination of joints, and bones of a body of the one or more potential occupants.

[0016] In some embodiments, the system further includes a learning engine configured to process the one or more received images to determine the occupancy in the ROI. The learning engine is configured to be trained based on any one or a combination of simulated datasets and historical datasets.

[0017] In some embodiments, the learning engine includes machine learning based components selected from any one or a combination of convolution neural network, auxiliary neural network, and random forest classifier.

[0018] In some embodiments, the system further includes a database communicably coupled to the computing device. The database is configured to store one or more datasets including information pertaining to pose attributes and skeletal attributes. The computing device is configured to determine the one or more potential occupants based on a mapping of determined first and second attributes with the pose and skeletal attributes, respectively stored in the database.

[0019] In a second aspect, the present disclosure provides a method for determining occupancy in a region of interest (ROI). The method includes receiving, at a computing device, from one or more visual sensors disposed in the ROI, one or more visual images of the ROI. The method further includes generating, at the computing device, from the one or more images, a heat map of the ROI. The method further includes determining, at the computing device, from the heat map of the ROI, a first set of attributes indicative of presence of one or more potential occupants in the ROI. The first set of attributes is based on pose attributes of the one or more potential occupants. The method further includes determining, at the computing device, from the heat map of the ROI and the first set of attributes, a second set of attributes indicative of presence of the one or more potential occupants in the ROI. The second set of attributes is based on skeletal attributes of the one or more potential occupants in the ROI. The method further includes determining, at the computing device, based on any one or both of the first and second attributes, an estimated pose of the one or more potential occupants in the ROI. The method further includes determining, at the computing device, the occupancy in the ROI based on a number of distinct estimated poses determined. [00201 In some embodiments, the pose attributes include a plurality of possible poses of the one or more potential occupants in the ROI.

[0021] In some embodiments, the skeletal attributes include relative location and identity of any one or a combination of joints, and bones of a body of the one or more potential occupants.

[0022] In a third aspect, the present disclosure provides a vehicle including the system for determining occupancy in a region of interest of the first aspect.

[0023] Various objects, features, aspects, and advantages of the inventive subject matter will become more apparent from the following detailed description of preferred embodiments, along with the accompanying drawing figures in which like numerals represent like components. BRIEF DESCRIPTION OF DRAWINGS

[0024] The accompanying drawings are included to provide a further understanding of the present disclosure and are incorporated in and constitute a part of this specification. The drawings illustrate exemplary embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0025] FIG. 1 illustrates a schematic block diagram of a system for determining occupancy in a region of interest (ROI), according to an embodiment of the present disclosure;

[0026] FIG. 2 illustrates a schematic flow diagram for a method for determining occupancy in a region of interest (ROI), according to an embodiment of the present disclosure;

[0027] FIGs. 3A - 3D illustrate exemplary images of a region of interest depicting analysis of a heat map of the ROI in order to determine first and / or second attributes;

[0028] FIG. 3E illustrates an exemplary schematic flow diagram for a process to determine occupancy in the ROI;

[0029] FIG. 3F illustrates a schematic representation of selection of a structure with higher likelihood for determining occupancy in the ROI;

[0030] FIGs. 4A - 4D illustrate exemplary images of a region of interest where the system of FIG. 1 is applied to determine occupancy in the region of interest;

[0031] FIG. 4E illustrates an exemplary estimation of pose determined from the images of FIGs. 4A - 4D, by the system of FIG. 1 for determining occupancy in a region of interest;

[0032] FIG. 4F illustrates a conventional estimation of pose determined from the images of FIGs. 4A - 4C, by a conventional system to determine occupancy in a region of interest; and

[0033] FIG. 5 illustrates an exemplary schematic block diagram of a hardware platform for implementation of the system of FIG. 1. DETAILED DESCRIPTION

[0034] The following is a detailed description of embodiments of the disclosure depicted in the accompanying drawings. The embodiments are in such details as to clearly communicate the disclosure. However, the amount of detail offered is not intended to limit the anticipated variations of embodiments; on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the present disclosure as defined by the appended claims.

[0035] In a first aspect, the present disclosure provides a system for determining occupancy in a region of interest (ROI). The system includes a computing device including a processor and a memory communicably coupled to the processor, the memory storing instructions executable by the processor. The computing device is configured to receive, from one or more visual sensors disposed in the ROI, one or more visual images of the ROI. The computing device is further configured to generate, from the one or more images, a heat map of the ROI. The computing device is further configured to determine, from the heat map of the ROI, a first set of attributes indicative of presence of one or more potential occupants in the ROI. The first set of attributes is based on pose attributes of the one or more potential occupants. The computing device is further configured to determine, from the heat map of the ROI and the first set of attributes, a second set of attributes indicative of presence of the one or more potential occupants in the ROI. The second set of attributes is based on skeletal attributes of the one or more potential occupants in the ROI. The computing device is further configured to determine, based on any one or both of the first and second attributes, an estimated pose of the one or more potential occupants in the ROI. The computing device is configured to determine the occupancy in the ROI based on a number of distinct estimated poses determined.

[0036] In some embodiments, the pose attributes include a plurality of possible poses of the one or more potential occupants in the ROI.

[0037] In some embodiments, the skeletal attributes include relative location and identity of any one or a combination of joints, and bones of a body of the one or more potential occupants.

[0038] In some embodiments, the system further includes a learning engine configured to process the one or more received images to determine the occupancy in the ROI. The learning engine is configured to be trained based on any one or a combination of simulated datasets and historical datasets.

[0039] In some embodiments, the learning engine includes machine learning based components selected from any one or a combination of convolution neural network, auxiliary neural network, and random forest classifier.

[0040] In some embodiments, the system further includes a database communicably coupled to the computing device. The database is configured to store one or more datasets including information pertaining to pose attributes and skeletal attributes. The computing device is configured to determine the one or more potential occupants based on a mapping of determined first and second attributes with the pose and skeletal attributes, respectively stored in the database.

[0041] In a second aspect, the present disclosure provides a method for determining occupancy in a region of interest (ROI). The method includes receiving, at a computing device, from one or more visual sensors disposed in the ROI, one or more visual images of the ROI. The method further includes generating, at the computing device, from the one or more images, a heat map of the ROI. The method further includes determining, at the computing device, from the heat map of the ROI, a first set of attributes indicative of presence of one or more potential occupants in the ROI. The first set of attributes is based on pose attributes of the one or more potential occupants. The method further includes determining, at the computing device, from the heat map of the ROI and the first set of attributes, a second set of attributes indicative of presence of the one or more potential occupants in the ROI. The second set of attributes is based on skeletal attributes of the one or more potential occupants in the ROI. The method further includes determining, at the computing device, based on any one or both of the first and second attributes, an estimated pose of the one or more potential occupants in the ROI. The method further includes determining, at the computing device, the occupancy in the ROI based on a number of distinct estimated poses determined.

[0042] In some embodiments, the pose attributes include a plurality of possible poses of the one or more potential occupants in the ROI.

[0043] In some embodiments, the skeletal attributes include relative location and identity of any one or a combination of joints, and bones of a body of the one or more potential occupants.

[0044] In a third aspect, the present disclosure provides a vehicle including the system for determining occupancy in a region of interest of the first aspect.

[0045] FIG. 1 illustrates a schematic block diagram of a system 100 for determining occupancy in a region of interest (ROI), according to an embodiment of the present disclosure. Occupancy may be defined as a number of occupants in the ROI. In some cases, occupants may include people, pets, etc. In some embodiments, the ROI may be a passenger cabin of a vehicle. In such embodiments, the system 100 may be deployed in the vehicle (such as a car, truck, etc.). Determining the occupancy accurately in the vehicle will allow features of the vehicle, such as advanced driver-assist system (ADAS), emergency braking systems, obstacle avoidance systems, air conditioning system, audio-visual system, safety systems, etc. to function optimally, particularly in case of autonomous or semi-autonomous vehicles.

[0046] The system 100 includes a computing device 102 configured to determine occupancy in the ROI. The computing device 102 may be communicably coupled with the one or more visual or image sensors provided in the ROI in order to capture images of the ROI. The system further includes a database 150 configured to store images captured by the one or more sensors.

[0047] The computing device 102 may include a processor 104 and a memory 106 communicably coupled to the processor 104. The memory 106 may store instructions executable by the processor 104 to enable the computing device 102 to determine occupancy in the ROI.

[0048] In some embodiments, the processor 104 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, logic circuitries, and / or any devices that process data based on operational instructions. Among other capabilities, the processor 104 may be configured to fetch and execute computer-readable instructions stored in the memory 106 for facilitating the system 100 to determine occupancy in the ROI. Any reference to a task in the present disclosure may refer to an operation being or that may be performed on data. The memory 106 may be configured to store one or more computer-readable instructions or routines in a non-transitory computer readable storage medium for determining occupancy in the ROI. The memory 106 may include any non-transitory storage device including, for example, volatile memory such as RAM, or non-volatile memory such as EPROM, flash memory, and the like. In some embodiments, the computing device 102 may include an interface 108. The interface 108 may include a variety of interfaces, for example, interfaces for data input and output devices, referred to as VO devices, storage devices, and the like. The interface 108 may also provide a communication pathway for one or more components of the computing device 102. Examples of such components include, but are not limited to, a processing engine 110 and the database 150. [00491 In some embodiments, the computing device 102 includes the processing engine 110. The processing engine 110 may be implemented as a combination of hardware and programming (for example, programmable instructions) to implement one or more functionalities of the processing engine 110. In examples described herein, such combinations of hardware and programming may be implemented in several different ways. For example, the programming for the processing engine 110 may be processor executable instructions stored on a non-transitory machine-readable storage medium and the hardware for the processing engine 110 may include a processing resource (for example, one or more processors), to execute such instructions. In the present examples, the machine-readable storage medium may store instructions that, when executed by the processing resource, implement the processing engine 110. In such examples, the computing device 102 may include the machine-readable storage medium storing the instructions and the processing resource to execute the instructions, or the machine-readable storage medium may be separate but accessible to the computing device 102 and the processing resource. In other examples, the processing engine 110 may be implemented by electronic circuitry.

[0050] The processing engine 110 includes an image receiving engine 112, a heat map engine 114, a first attributes engine 116, a second attributes engine 118, an occupancy determination engine 120, a learning engine 122, and other engine(s) 124. The other engine(s) 124 may include engines configured to perform one or more functions ancillary functions associated with the processing engine 110.

[0051] The image receiving engine 112 is configured to receive one or more images of the ROI in which an occupancy is to be determined. The one or more images are visual images. The one or more images may be still images or video. The one or more images may be recorded or captured by one or more sensors provided in the ROI. The one or more sensors may include image capture apparatuses, such as cameras.

[0052] The heat map engine 114 is configured to generate a heat map of the ROI based on the received one or more images of the ROI.

[0053] The first attributes engine 116 is configured to determine, from the heat map of the ROI, a first set of attributes indicative of presence of one or more potential occupants in the ROI. The first set of attributes is based on pose attributes of the one or more potential occupants. In some embodiments, the pose attributes include a plurality of possible poses of the one or more potential occupants in the ROI.

[0054] The second attributes engine 118 is configured to determine, from the heat map of the ROI and the first set of attributes, a second set of attributes indicative of presence of the one or more potential occupants in the ROI. The second set of attributes is based on skeletal attributes of the one or more potential occupants in the ROI. In some embodiments, the skeletal attributes include relative location and identity of any one or a combination of joints, and bones of a body of the one or more potential occupants.

[0055] The occupancy determination engine 120 is configured to determine, based on any one or both of the first and second attributes, an estimated pose of the one or more potential occupants in the ROI. The occupancy determination engine 120 is further configured to determine the occupancy in the ROI based on a number of distinct estimated poses determined.

[0056] In some embodiments, the learning engine 122 is configured to process the one or more received images to determine the occupancy in the ROI. The learning engine 122 is configured to be trained based on any one or a combination of simulated datasets and historical datasets. In some embodiments, the learning engine 122 includes machine learning (ML) based components selected from any one or a combination of convolution neural network (CNN), auxiliary neural network (ANN), and random forest (RF) classifier.

[0057] FIG. 2 illustrates a schematic flow diagram for a method 200 for determining occupancy in the ROI, according to an embodiment of the present disclosure. At step 202, the method 200 includes receiving, at the computing device 102, from the one or more visual sensors disposed in the ROI, one or more visual images of the ROI. At step 204, the method 200 further includes generating, at the computing device 102, from the one or more images, a heat map of the ROI. At step 206, the method 200 further includes determining, at the computing device 102, from the heat map of the ROI, a first set of attributes indicative of presence of one or more potential occupants in the ROI, wherein the first set of attributes is based on pose attributes of the one or more potential occupants. At step 208, the method 200 further includes determining 208, at the computing device 102, from the heat map of the ROI and the first set of attributes, a second set of attributes indicative of presence of the one or more potential occupants in the ROI, wherein the second set of attributes is based on skeletal attributes of the one or more potential occupants in the ROI. At step 210, the method 200 further includes determining, at the computing device 102, based on any one or both of the first and second attributes, an estimated pose of the one or more potential occupants in the ROI. At step 212, the method 200 further includes determining, at the computing device 102, the occupancy in the ROI based on a number of distinct estimated poses determined.

[0058] FIGs. 3A - 3D illustrate exemplary images 301, 302, 303, 304, respectively of a region of interest depicting analysis of a heat map of the ROI in order to determine first and / or second attributes. Referring to FIG. 3 A, the image 301 depicts a generated heat map of the ROI showing one occupant in an unusual pose.

[0059] Referring to FIG. 3B, the image 302 depicts pixel level ground truth annotations of the first attributes. Here, the first attributes are joints of the occupant.

[0060] Referring to FIG. 3C, the image 303 depicts heat map prediction for a joint (for example, a left elbow joint of the occupant).

[0061] Referring to FIG. 3D, the image 304 depicts a visualization of local peak predictions for the left elbow joint of the occupant.

[0062] The neural network tries to regress a Gaussian heat map for each joint of the occupant in the heat map. In order to estimate occupancy, the predicted joint location (such as the left elbow joint) is selected as the highest peak in the heat map.

[0063] FIG. 3E illustrates an exemplary schematic flow diagram for a process 310 to determine occupancy in the ROI. At step 312, input images of the region of interest are received. At step 314, the images are received by a neural network such as a human pose estimator. At step 316, the neural network generates a heat map for the received image. At step 318, a neural network, such as the auxiliary neural network further receives the imaged from the step 312. At step 320, from the images received by the auxiliary neural network, a structure correction module estimates first and second attributes indicative of presence of a potential occupant in the ROI by estimating skeletal and pose attributes. At step 322, the process 300 further estimates and refines pose and skeletal attributes to determine a pose and / or key points in the occupant, such as joint, bones, etc. At step 324, a random forest (RF) classifier is configured to analyze the refined first and second attributes. At step 326, based on analysis of the refined first and second attributes, the occupancy of the ROI is determined.

[0064] FIG. 3F illustrates a schematic representation of selection of a structure with higher likelihood for determining occupancy in the ROI. The auxiliary neural network is trained, so as to minimize an expected likelihood of data provided by the following equation. N-l £(joints,X,0) = ^JpN logq(yN\X,9) + filog q(ydyi+iX0)] pall i

[0065] Referring to FIG. 3F, a heat map is selected that may be a better fit for a learnt behavior of the neural network. In some cases, the neural network may be configured to select a better fit even when a peak is slightly lower.

[0066] FIG. 3F represents two structures - first structure depicted by Joint 1 - Joint 2A -Joint 3, and the second joint depicted by Joint 1 - Joint 2B - Joint 3.

[0067] Since the second structure displays a better fit, the neural network is configured to select the second structure even though the peak for Joint 2B is lower than that for Joint 2A.

[0068] FIGs. 4A - 4D illustrate exemplary images 401, 402, 403, 404, respectively, of a region of interest where the system 100 of FIG. 1 is applied to determine occupancy in the region of interest.

[0069] Referring to FIG. 4A, the image 401 represents a region of interest in a passenger cabin of a vehicle. As can be seen, the ROI includes one occupant.

[0070] Referring to FIG. 4B, the image 402 depicts a heat map and first attributes determined from the image 401 of FIG. 4A. A neural network, such as a conventional neural network may be used. The neural network may use human pose estimator (HPE) to determine the first attributes based on pose of the occupant.

[0071] Referring to FIG. 4C, the image 403 depicts the second attributes determined from the image 402 of FIG. 4B. A neural network, such as an auxiliary neural network may be used. The neural network may try to regress a gaussian heat map to determine each second attribute. The second attributes may include key points, such as joints, bones, etc.

[0072] Referring to FIG. 4D, the image 404 depicts structure correction, wherein the estimated pose of the occupant is determined based on matching with a database including existing pose attributes of occupants. The pose correction may facilitate accurate prediction of occupancy in case of any inconsistencies in either or both of the first and second attributes.

[0073] FIG. 4E illustrates an exemplary estimation of pose 410 determined from the images of FIGs. 4A - 4D, by the system 100 of FIG. 1 for determining occupancy in a region of interest. The pose 410 determined by the system 100 shows that the ROI includes one occupant as the system 100 is able to estimate a correct pose of the occupant.

[0074] FIG. 4F illustrates a conventional estimation of pose 450 determined from the images of FIGs. 4A - 4C, by a conventional system to determine occupancy in a region of interest. The pose 450 may not be accurately determined, and there may be a chance that conventional systems may indicate that there is no occupant in the ROI.

[0075] FIG. 5 illustrates an exemplary schematic block diagram of a hardware platform for implementation of the system 100. As shown in FIG. 5, a computer system 500 can include an external storage device 510, a bus 520, a main memory 530, a read only memory 540, a mass storage device 550, communication port 560, and a processor 570. A person skilled in the art will appreciate that the computer system may include more than one processor and communication ports. Examples of processor 570 include, but are not limited to, an Intel® Itanium® or Itanium 2 processor(s), or AMD® Opteron® or Athlon MP® processor(s), Motorola® lines of processors, FortiSOC™ system on chip processors or other future processors. Processor 570 may include various modules associated with embodiments of the present invention. Communication port 560 can be any of an RS-232 port for use with a modem-based dialup connection, a 10 / 100 Ethernet port, a Gigabit or 10 Gigabit port using copper or fibre, a serial port, a parallel port, or other existing or future ports. Communication port 560 may be chosen depending on a network, such a Local Area Network (LAN), Wide Area Network (WAN), or any network to which computer system connects. Memory 530 can be Random Access Memory (RAM), or any other dynamic storage device commonly known in the art. Read-only memory 540 can be any static storage device(s) e.g., but not limited to, a Programmable Read Only Memory (PROM) chips for storing static information e.g., start-up or BIOS instructions for processor 570. Mass storage 550 may be any current or future mass storage solution, which can be used to store information and / or instructions. Exemplary mass storage solutions include, but are not limited to, Parallel Advanced Technology Attachment (PATA) or Serial Advanced Technology Attachment (SATA) hard disk drives or solid-state drives (internal or external, e.g., having Universal Serial Bus (USB) and / or Firewire interfaces), e.g. those available from Seagate (e.g., the Seagate Barracuda 7102 family) or Hitachi (e.g., the Hitachi Deskstar 7K1000), one or more optical discs, Redundant Array of Independent Disks (RAID) storage, e.g. an array of disks (e.g., SATA arrays), available from various vendors including Dot Hill Systems Corp., LaCie, Nexsan Technologies, Inc. and Enhance Technology, Inc.

[0076] Bus 520 communicatively couples processor(s) 570 with the other memory, storage, and communication blocks. Bus 520 can be, e.g., a Peripheral Component Interconnect (PCI) / PCI Extended (PCLX) bus, Small Computer System Interface (SCSI), USB or the like, for connecting expansion cards, drives and other subsystems as well as other buses, such a front side bus (FSB), which connects processor 570 to software system.

[0077] Optionally, operator and administrative interfaces, e.g., a display, keyboard, and a cursor control device, may also be coupled to bus 520 to support direct operator interaction with a computer system. Other operator and administrative interfaces can be provided through network connections connected through communication port 560. The external storage device 510 can be any kind of external hard-drives, floppy drives, IOMEGA® Zip Drives, Compact Disc - Read Only Memory (CD-ROM), Compact Disc-Re-Writable (CD-RW), Digital Video Disk-Read Only Memory (DVD-ROM). Components described above are meant only to exemplify various possibilities. In no way should the aforementioned exemplary computer system limit the scope of the present disclosure.

[0078] It should be apparent to those skilled in the art that many more modifications besides those already described are possible without departing from the inventive concepts herein. The inventive subject matter, therefore, is not to be restricted except in the spirit of the appended claims. Moreover, in interpreting both the specification and the claims, all terms should be interpreted in the broadest possible manner consistent with the context. In particular, the terms “comprise” and “comprising” should be interpreted as referring to elements, components, or steps in a non-exclusive manner, indicating that the referenced elements, components, or steps may be present, or utilized, or combined with other elements, components, or steps that are not expressly referenced. Where the specification claims refer to at least one of something selected from the group consisting of A, B, C ....and N, the text should be interpreted as requiring only one element from the group, not A plus N, or B plus N, etc. The foregoing description of the specific embodiments will so fully reveal the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and / or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the spirit and scope of the appended claims.

[0079] While the foregoing describes various embodiments of the invention, other and further embodiments of the invention may be devised without departing from the basic scope thereof. The scope of the invention is determined by the claims that follow. The invention is not limited to the described embodiments, versions, or examples, which are included to enable a person having ordinary skill in the art to make and use the invention when combined with information and knowledge available to the person having ordinary skill in the art. ADVANTAGES OF INVENTION

[0080] The present invention provides a system and a method for determining an occupancy in a region of interest.

[0081] The present invention provides a system for accurately determining presence of one or more occupants in a region of interest irrespective of a pose adopted by the one or more occupants.

[0082] The present invention provides a system for limiting false positives and false negatives of occupancy in the ROI.

[0083] The present invention provides a system having a structure correction mechanism to counter any misprediction of joints from the pose estimation neural network.

Claims

1. A system (100) for determining occupancy in a region of interest (ROI), the system (100) comprising:a computing device (102) comprising a processor (104) and a memory (106) communicably coupled to the processor (104), the memory (106) storing instructions executable by the processor (104), the computing device (102) configured to:receive, from one or more visual sensors disposed in the ROI, one or more visual images of the ROI;generate, from the one or more images, a heat map of the ROI;determine, from the heat map of the ROI, a first set of attributes indicative of presence of one or more potential occupants in the ROI, wherein the first set of attributes is based on pose attributes of the one or more potential occupants;determine, from the heat map of the ROI and the first set of attributes, a second set of attributes indicative of presence of the one or more potential occupants in the ROI, wherein the second set of attributes is based on skeletal attributes of the one or more potential occupants in the ROI; anddetermine, based on any one or both of the first and second attributes, an estimated pose of the one or more potential occupants in the ROI,wherein the computing device (102) is configured to determine the occupancy in the ROI based on a number of distinct estimated poses determined.

2. The system (100) as claimed in claim 1, wherein the pose attributes comprise a plurality of possible poses of the one or more potential occupants in the ROI.

3. The system (100) as claimed in claim 1, wherein the skeletal attributes comprise relative location and identity of any one or a combination of joints, and bones of a body of the one or more potential occupants.

4. The system (100) as claimed in claim 1, wherein the system (100) further comprises a learning engine (122) configured to process the one or more received images to determine the occupancy in the ROI, and wherein the learning engine (122) is configured to be trained based on any one or a combination of simulated datasets and historical datasets.

5. The system (100) as claimed in claim 3, wherein the learning engine (122) comprises machine learning (ML) based components selected from any one or a combination of convolution neural network (CNN), auxiliary neural network (ANN), and random forest (RF) classifier.

6. The system (100) as claimed in claim 1, wherein the system (100) further comprises a database (150) communicably coupled to the computing device (102), wherein the database (150) is configured to store one or more datasets comprising information pertaining to pose attributes and skeletal attributes, and wherein the computing device (102) is configured to determine the one or more potential occupants based on a mapping of determined first and second attributes with the pose and skeletal attributes, respectively stored in the database (150).

7. A method (200) for determining occupancy in a region of interest (ROI), the method (200) comprising:receiving (202), at a computing device (102), from one or more visual sensors disposed in the ROI, one or more visual images of the ROI;generating (204), at the computing device (102), from the one or more images, a heat map of the ROI;determining (206), at the computing device (102), from the heat map of the ROI, a first set of attributes indicative of presence of one or more potential occupants in the ROI, wherein the first set of attributes is based on pose attributes of the one or more potential occupants;determining (208), at the computing device (102), from the heat map of the ROI and the first set of attributes, a second set of attributes indicative of presence of the one or more potential occupants in the ROI, wherein the second set of attributes is based on skeletal attributes of the one or more potential occupants in the ROI;determining (210), at the computing device (102), based on any one or both of the first and second attributes, an estimated pose of the one or more potential occupants in the ROI; anddetermining (212), at the computing device (102), the occupancy in the ROI based on a number of distinct estimated poses determined.

8. The method (200) as claimed in claim 7, wherein the pose attributes comprise a plurality of possible poses of the one or more potential occupants in the ROI.

9. The method (200) as claimed in claim 7, wherein the skeletal attributes comprise relative location and identity of any one or a combination of joints, and bones of a body of the one or more potential occupants.

10. A vehicle comprising the system (100) for determining occupancy in a region of interest (ROI) of claim 1.18

Images