System and method for detecting convex mirrors in images

Abstract

To provide a system and method for detecting a curved mirror in an image.SOLUTION: A system and a computer implemented method of detecting curved mirrors (814) in an image are provided. The method comprises the steps of: applying a machine learned algorithm on the image (802) to identify a curved mirror candidate (800) within the image (802); and applying an anomaly detection algorithm on the identified curved mirror candidate (800) to verify whether the curved mirror candidate (800) is a curved mirror (814).SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates generally to a system and computer-implemented method for detecting convex mirrors in an image. [Background technology]

[0002] Road traffic accidents tend to occur at and around road intersections and at points on roads, such as at sharp bends, where it is difficult for vehicles to see traffic coming from different directions. In particular, the number of accidents at intersections without traffic lights is generally higher than at intersections with traffic lights.

[0003] To reduce the number of accidents at intersections, especially those without traffic lights, road safety mirrors, such as convex mirrors, are typically installed at intersections and at points on roads where there are sharp curves, for example. Such convex mirrors allow vehicles to see blind spots and the like that exist at these intersections and points, thereby allowing road users to feel safe and avoid or reduce the occurrence of accidents. Naturally, convex mirrors are located on the exterior of the vehicle.

[0004] It has been proposed to provide vehicles with image capture devices, e.g., video cameras, to detect convex mirrors at certain points on the road, e.g., at intersections and sharp turns, etc. Convex mirror detection plays an important role in blind spot detection.

[0005] It has been recognized that improvements to existing Advanced Driver Assistance Systems (ADAS) are desirable. In particular, existing object recognition technology can be improved to accommodate real-time convex mirror recognition for use in ADAS.

[0006] For example, existing ADAS systems cannot quickly detect convex mirrors in real time. Furthermore, the accuracy of existing systems is problematic because many of the convex mirrors they detect are false positives. Accurate detection of convex mirrors is difficult because convex mirrors simply reflect an image of the surrounding area where they are located and do not have any fixed pattern.

[0007] Furthermore, the inventors have realized that the computation speed of convex mirror detection can also affect collision risk prediction. Because the computational load increases as the detection system becomes more complex, the computation speed of convex mirror detection tends to become slower. One problem that can arise is that with current convex mirror detection, it can take a considerable amount of time before a convex mirror is detected. [Prior art documents] [Non-patent literature]

[0008] [Non-Patent Document 1] Redmon, Joseph & Farhadi, Ali. (2018). Yolov3: An Incremental Improvement [Non-patent document 2] Ammar A,Koubaa A,Ahmed M,Saad A,Benjdira B.Vehicle Detection from Aerial Images Using Deep Learning:A Comparative Study.Electronics.2021:10(7):820 [Non-patent document 3] Zong.B.,Song.Q.,Min.M.,Cheng.W.,Lumezanu,C.,Cho.D.,&Chen.H.(2018).Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection.ICLR Summary of the Invention [Problem to be solved by the invention]

[0009] Therefore, there is a need for a system and computer-implemented method for detecting convex mirrors in images that addresses, or at least attempts to ameliorate, one of the problems discussed above. [Means for solving the problem]

[0010] According to one aspect of the present disclosure, a computer-implemented method for detecting convex mirrors in an image is provided, comprising the steps of applying a machine learning algorithm to the image to identify potential convex mirrors in the image, and applying an anomaly detection algorithm to the identified potential convex mirrors to determine whether the potential convex mirrors are convex mirrors.

[0011] The anomaly detection algorithm of the methods disclosed herein may be based on the Deep Autoencoder Gaussian Mixture Model (DAGMM).

[0012] A convex mirror candidate in the methods disclosed herein can be confirmed as a convex mirror if it cannot be a traffic sign.

[0013] The anomaly detection algorithm of the method disclosed herein includes the steps of applying an autoencoder function to image data associated with a convex mirror candidate to obtain a point on a transformation map, the point representing the convex mirror candidate on the transformation map; and determining whether the point is from a cluster representing a traffic sign on the transformation map. Threshold Beyond the value distance Away and if so, confirming the convex mirror candidate as a convex mirror.

[0014] There can be multiple clusters representing traffic signs, and a convex mirror candidate is one whose point is located in each of the clusters. Threshold Beyond the value distance Away If there is a curved mirror, it will be confirmed.

[0015] A machine learning algorithm can be trained using bounding boxes with parameters optimized for convex mirrors.

[0016] The parameters optimized for the convex mirror are the bounding box height, the bounding box width, the abscissa of the center point of the bounding box, the ordinate of the center point of the bounding box, and the ratio of the bounding box height to the Width It may include ratios.

[0017] The method may further include acquiring the image using an image capture device.

[0018] Acquiring the images may include acquiring multiple images over different time instances.

[0019] The image may be a real-time image.

[0020] According to another aspect of the present disclosure, there is provided a system for detecting convex mirrors in an image, the system including an image capture device and an electronic control unit coupled to the image capture device, the image capture device configured to acquire the image, the electronic control unit configured to apply a machine learning algorithm to the image to identify potential convex mirrors in the image, and apply an anomaly detection algorithm to the identified potential convex mirrors to confirm whether the potential convex mirrors are convex mirrors.

[0021] The anomaly detection algorithm of the system disclosed herein may be based on the Deep Autoencoder Gaussian Mixture Model (DAGMM).

[0022] A convex mirror candidate in the system disclosed herein can be identified as a convex mirror when it cannot be a traffic sign.

[0023] The anomaly detection algorithm of the system disclosed herein includes the steps of applying an autoencoder function to image data associated with the convex mirror candidate to obtain a point on a transformation map, the point representing the convex mirror candidate on the transformation map, and determining whether the point is from a cluster representing a traffic sign on the transformation map. Threshold Beyond the value distance Away If there is a candidate convex mirror, confirming the candidate convex mirror as a convex mirror.

[0024] According to another aspect of the present disclosure, there is provided a computer-readable storage medium having stored thereon instructions for instructing a processing unit of the system to perform a computer-implemented method for detecting convex mirrors in an image, the method comprising the steps of applying a machine learning algorithm to the image to identify potential convex mirrors in the image, and applying an anomaly detection algorithm to the identified potential convex mirrors to determine whether the potential convex mirrors are convex mirrors.

[0025] Exemplary embodiments of the present invention will be better understood and readily apparent to those skilled in the art from the following description, which is given by way of example only, and taken in conjunction with the drawings in which: [Brief explanation of the drawings]

[0026] [Figure 1] FIG. 1 is a schematic block diagram illustrating a system for detecting convex mirrors in an image in an exemplary embodiment. [Figure 2] 1 is a schematic flowchart illustrating a computer-implemented method for detecting convex mirrors in an image in an exemplary embodiment. [Figure 3] 1 shows a series of images illustrating dataset creation for detecting road safety mirrors, e.g., convex mirrors, using machine learning algorithms in an exemplary embodiment; [Figure 4] 10 is a frame shot of a verification result of road safety mirror detection in an exemplary embodiment. [Figure 5]10 shows a series of images depicting examples of true positive images in the form of road safety mirrors detected by an illustrative embodiment; [Figure 6] 10 shows a series of images depicting examples of false positive images in the form of road traffic signs detected in accordance with an illustrative embodiment; [Figure 7] 10 is a transformation map including data points for convex mirror candidates identified in an image in an exemplary embodiment; [Figure 8] 1 is a diagram illustrating an improved anomaly detection method in an example embodiment. [Figure 9] 10 is a photograph illustrating the effectiveness of an improved anomaly detection method in an exemplary embodiment. [Figure 10] 10A-10C are diagrams and photographs illustrating road safety mirror detection at a T-junction in an exemplary embodiment; [Figure 11] 10 is a chart illustrating dimensions of a convex mirror relative to dimensions of a default box for model training in an exemplary embodiment. [Figure 12] 1 is a schematic diagram of a computer system suitable for implementing the exemplary embodiments. DETAILED DESCRIPTION OF THE INVENTION

[0027] Exemplary non-limiting embodiments may provide a system and computer-implemented method for detecting road safety mirrors, such as convex mirrors, in an image.

[0028] In various embodiments, the term "convex mirror," as used herein, broadly refers to a mirror having a curved reflective surface. In various embodiments, the convex mirror includes a curved mirror portion. In various embodiments, the surface is convex (i.e., protruding outward). In various embodiments, the convex mirror is a convex mirror.

[0029] In various embodiments, the terms "image" or "image data," as used herein, broadly refer to any content or data that can be rendered for viewing by a user. In various embodiments, the image or image data includes computer-readable data. In various embodiments, the image or image data may be converted into computer-readable data. In various embodiments, the image or image data may be converted into a format suitable or compatible for use by components of the systems and methods disclosed herein. For example, the image or image data may be a frame from a video, a portion of that frame from a video, a still image, a portion of a still image, or the like.

[0030] 1 is a schematic block diagram illustrating a system 100 for detecting convex mirrors in an image in an exemplary embodiment. The system 100 is mounted on a vehicle and includes an image capture device 102 and a processing unit 104 coupled to the image capture device 102.

[0031] In an exemplary embodiment, image capture device 102 is configured to capture images. The vehicle's image capture device 102 may be a camera or video camera located near the front of the vehicle body, near the rearview mirror, or on the vehicle's front grille. Image capture device 102 is positioned so that its image capture area is at a predetermined angle toward the front of the vehicle.

[0032] In an exemplary embodiment, processing unit 104 may be configured to control the function of components of system 100. In an exemplary embodiment, processing unit 104, e.g., a vehicle's electronic control unit (ECU), is configured to apply machine learning algorithms to the images to identify potential convex mirrors in the images and to apply anomaly detection algorithms to the identified potential convex mirrors to determine whether the potential convex mirrors are convex mirrors.

[0033] In an exemplary embodiment, the anomaly detection algorithm may be based on a Deep Autoencoder Gaussian Mixture Model (DAGMM). The anomaly detection algorithm may be configured to identify a convex mirror candidate as a convex mirror when it cannot be a road sign. For example, the anomaly detection algorithm may include applying an autoencoder function to image data associated with the convex mirror candidate to obtain a point, e.g., a data point, on a transformation map, the point representing the convex mirror candidate on the transformation map; and determining whether the point falls within a cluster representing a traffic sign on the transformation map. Threshold distance Beyond the distance Away stomach If and confirming the convex mirror candidate as a convex mirror. In an exemplary embodiment, there may be multiple clusters of points representing traffic signs. A convex mirror candidate is one whose point is in each of the clusters. Threshold Beyond the value distance Away If there is one, it will be identified as a curve mirror.

[0034] In an exemplary embodiment, processing unit 104 may be further coupled to object detection unit 106, which may be further coupled to action unit 108. Object detection unit 106 may be configured to perform object detection on convex mirrors detected by processing unit 104. Action unit 108 may be configured to receive one or more commands from object detection unit 106, such as, but not limited to, to activate a braking function of the vehicle, and / or activate a warning system for a vehicle user, and / or perform steering control, or to take no action.

[0035] During operation, a crossroads or intersections may be identified by image capture device 102. In some exemplary embodiments, map information may be provided to processing unit 104, which may use the map information to identify crossroads or intersections, for example, by matching the map with Global Positioning System (GPS) coordinates. At such crossroads or intersections, processing unit 104 applies machine learning algorithms to images captured by image capture device 102 to identify potential convex mirrors in the images, and then applies anomaly detection algorithms to the identified potential convex mirrors to confirm whether the potential convex mirrors are convex mirrors.

[0036] 2 is a schematic flowchart 200 illustrating a computer-implemented method for detecting convex mirrors in an image in an exemplary embodiment. In step 202, a machine learning algorithm is applied to the image to identify potential convex mirrors in the image. In step 204, an anomaly detection algorithm is applied to the identified potential convex mirrors to confirm whether the potential convex mirrors are convex mirrors. The method for detecting convex mirrors in an image may be implemented using system 100 of FIG. 1. For example, the identification and confirmation of potential convex mirrors in the image may be performed by processing unit 104.

[0037] In an exemplary embodiment, the method may further include capturing / acquiring images using an image capture device. The image capture device may be a camera or a video camera. The image capture device may be mounted on a vehicle and positioned in front of the vehicle body near a rearview mirror or on the vehicle's front grille. Capturing the images may include capturing a forward-looking image facing forward of the vehicle. Capturing the images may include capturing multiple images across different time instances. For example, the multiple images across different time instances may be a time-continuous series of frames from a video, with each frame representing an image captured at a particular time instance. The images may be real-time images. The images may be frames obtained from a real-time video.

[0038] In exemplary embodiments, no convex mirror candidates may be identified in the image. In exemplary embodiments, one or more convex mirror candidates may be identified in the image. In exemplary embodiments, no convex mirrors may be identified from one or more convex mirror candidates identified in the image. In exemplary embodiments, one or more convex mirrors may be identified from one or more convex mirror candidates identified in the image.

[0039] In an exemplary embodiment, the machine learning algorithm may be a real-time object detection system. The real-time object detection system may be a one-pass object detection system in which an image is analyzed only once. The real-time object detection system may be a You Only Look Once (YOLO) v3 system. In an exemplary embodiment, the machine learning algorithm may be trained using bounding boxes with parameters optimized for the convex mirror. The parameters optimized for the convex mirror include the height of the bounding box, the width of the bounding box, the abscissa of the center point of the bounding box, the ordinate of the center point of the bounding box, and the height of the bounding box. Width It may include ratios.

[0040] In an exemplary embodiment, the anomaly detection algorithm may be based on the likelihood that the convex mirror candidate is not a traffic sign. The anomaly detection algorithm may be based on a Deep Autoencoder Gaussian Mixture Model (DAGMM). In an exemplary embodiment, the anomaly detection algorithm includes applying an autoencoder function to image data associated with the convex mirror candidate to transform the candidate into a different domain to obtain a point on a transformation map, the point representing the convex mirror candidate on the transformation map; and determining whether the point is from a cluster representing a traffic sign on the transformation map. Threshold Beyond the value distance Awayand if so, confirming the convex mirror candidate as a convex mirror. In an exemplary embodiment, there may be multiple clusters of points representing traffic signs. A convex mirror candidate is one whose point is in each of the clusters. Threshold Beyond the value distance Away If there is one, it will be identified as a curve mirror.

[0041] 3A-3C show a series of images illustrating the creation of a dataset for road safety mirror, e.g., convex mirror, detection using a machine learning algorithm in an exemplary embodiment. In the exemplary embodiment, the machine learning algorithm used for road safety mirror detection is based on a real-time object detection system known as You Only Look Once (YOLO) v3. In the exemplary embodiment, the latest version as of 2019 was selected.

[0042] FIG. 3A shows an original image captured by an image capture device in its original pixel size. For training data, a high-resolution pixel image (approximately 12 million pixels) can be used. As shown in FIG. 3A, the Region of Interest (ROI) information of the road safety mirror is included in the original image. The ROI refers to the region of interest of the target object, i.e., the area of ​​the road safety mirror, which is enclosed by a box 302 in FIG. 3A. FIG. 3B shows a predetermined reduced pixel size image scaled down from the original image of FIG. 3A. FIG. 3C shows the L image to be used for the training dataset. * a * b * Figure 3C shows an image in color space converted from the reduced pixel size image of Figure 3B.

[0043] In an exemplary embodiment, the original image of FIG. 3A is scaled to a predetermined reduced pixel size of FIG. 3B and the L of FIG. 3C * a * b * As those skilled in the art will appreciate, the RGB color space is based on the colors red, green, and blue. * a * b *In color space, capital L * means brightness, and lowercase a * , b * means complementary colors. * a * b * I noticed that the color space seems to be close to human vision. In the RGB color space, it can be difficult to distinguish the color gamut depending on the brightness situation. On the other hand, L * a * b * In color space, it may be possible to distinguish color regions like the human eye. Therefore, in an exemplary embodiment, the original image is converted to L for use as input for the YOLOv3 deep learning method. * a * b * converted to color space.

[0044] FIG. 4 is a frame shot of a verification result of road safety mirror detection in an exemplary embodiment. A public road driving test was conducted using an exemplary embodiment of the systems and methods disclosed herein. In the exemplary implementation, a low-resolution camera (approximately, about 320,000 pixels) was used as the image capture device, i.e., not a high-resolution camera used for data collection. In the exemplary implementation, an NVIDIA Jetson Xavier module was used as the processing unit, e.g., controller. The road safety mirrors detected by the exemplary implementation are surrounded by boxes 402 and 404 shown in FIG. 4.

[0045] Figures 5A and 5B show a series of images representing examples of true positive images in the form of road safety mirrors detected by an exemplary embodiment, and Figures 6A-6D show a series of images representing examples of false positive images in the form of road traffic signs detected by an exemplary embodiment.

[0046] Despite using a low-resolution camera (approximately 320,000 pixels), the results showed a high accuracy of over 95%, as shown in Table 1 and equation (1).

number

[0047] [Table 1]

[0048] As can be seen from the results in Table 1, there is some FP in the results of road safety mirror detection.

[0049] Exemplary embodiments of the systems and methods disclosed herein further provide a solution to the problem of false positive results, as will be described below with reference to FIGS.

[0050] FIG. 7 is a transformation map 700 including data points, eg, 702a and 704a, of potential convex mirrors identified in an image in an exemplary embodiment.

[0051] 7, the transformation map 700 includes a first data point 702a representing a first traffic sign 702b, a second data point 704a representing a second traffic sign 704b, and a cluster 706 of data points representing, for example, a first convex mirror 708, shown on the image as a circle, and a second convex mirror 710, shown as an oval. Each data point on the transformation map 700 is obtained by applying an anomaly detection method to image data associated with a potential convex mirror. The first data point 702a and the second data point 704a are examples of false positive results that do not represent convex mirrors.

[0052] Anomaly detection methods can be used as a countermeasure to overcome the problem of false positive results. An example of an anomaly detection method is the Deep Autoencoder Gaussian Mixture Model (DAGMM). By using the Gaussian Mixture Model, one data point can be obtained for each object, and clusters of data points can be obtained for multiple objects on the transformation map 700.

[0053] However, the inventors have realized that even with existing anomaly detection methods such as DAGMM, it is difficult to define the distribution of road safety mirrors compared to traffic signs due to the dynamic and inconsistent images reflected from the road safety mirrors. Unlike traffic signs, which typically display a consistent pattern, convex mirrors do not have a fixed pattern but reflect images of the surrounding area where they are located. Therefore, there is no consistent pattern displayed by convex mirrors.

[0054] To overcome the difficulty in distinguishing between true and false positive results, the inventors have devised an improved anomaly detection algorithm.

[0055] 8 is a schematic diagram illustrating an improved anomaly detection method in an exemplary implementation. In the exemplary implementation, the improved anomaly detection method is based on DAGMM.

[0056] In an exemplary implementation, convex mirror candidates 800 are identified from an image 802. The convex mirror candidates 800 may be detected by applying a machine learning algorithm, such as the deep learning method YOLOv3, to the image 802. The convex mirror candidates 800 may be either road traffic signs (i.e., false positives) or convex mirrors (i.e., true positives). One or more convex mirror candidates 800 may be identified from the image 802. For example, there are two convex mirror candidates in the image 802, represented by two boxes 804 and 806.

[0057] The improved anomaly detection method then includes the steps of applying an autoencoder function to image data associated with the convex mirror candidate 800 to obtain data points (e.g., 808, 810) on a transformation map 812, where the data points (e.g., 808, 810) represent the convex mirror candidate 800 on the transformation map 812; and extracting the data points (e.g., 808) from a cluster representing a traffic sign on the transformation map 812. Threshold Beyond the value distance Away If so, confirming the convex mirror candidate 800 as a convex mirror 814.

[0058] As shown in FIG. 8 , there are multiple clusters (e.g., 816, 818) representing traffic signs 820. If a data point in a cluster (e.g., 816, 818) represents a traffic sign, a data point close to the cluster may be a traffic sign, while a data point far from the cluster may be a road safety mirror, e.g., a convex mirror. Therefore, in an exemplary implementation, the distance of a data point to a cluster representing a road traffic sign is calculated. If the distance of a data point to a cluster representing a traffic sign exceeds a predetermined threshold, the convex mirror candidate is considered to be a road safety mirror. If the distance of a data point to a cluster representing a traffic sign is within a predetermined threshold, the convex mirror candidate is considered not to be a road safety mirror. In other words, a convex mirror candidate 800 is calculated by calculating whether a data point, e.g., 808, is from each of the clusters (e.g., 816, 818). Threshold Beyond the value distance Away If so, it is confirmed as a convex mirror 814. In general, the threshold distance used to confirm a convex mirror candidate may depend on factors such as the resolution of the camera used. Thus, in various exemplary implementations, the threshold distance for confirming a convex mirror candidate may be adjusted and optimized to maximize true positive results and minimize false positive results of convex mirror detection.

[0059] 9A and 9B are photographs illustrating the effectiveness of the improved anomaly detection method in an exemplary implementation. FIG. 9A shows an image taken from a portion of a video (i.e., a sequence of frames / images) obtained without an improved anomaly detection method, e.g., DAGMM. Because no anomaly detection was applied, there were 31 false positive detections in this video. On the other hand, FIG. 9B shows an image taken from the same portion of a video obtained with an improved anomaly detection method, e.g., DAGMM. As shown in FIG. 9B, there were no false positive detections in the same video. Therefore, the effectiveness of the improved anomaly detection method disclosed herein was demonstrated by this video.

[0060] 10 is a diagram and photograph showing the detection of road safety mirrors at a T-junction in an exemplary embodiment. In the exemplary embodiment, road safety mirror detection by a method applying the improved anomaly detection algorithm DAGMM was confirmed after the subject vehicle 1000 approached the T-junction. Two road safety mirrors were identified, as indicated by boxes 1002 and 1004. Therefore, it has been demonstrated that the system and method for detecting convex mirrors disclosed herein are effective in reducing false positive results in road safety mirror detection and can successfully detect road safety mirrors.

[0061] 11 is a chart showing dimensions of a convex mirror relative to dimensions of a default box for model training in an exemplary embodiment. In an exemplary embodiment, a machine learning algorithm can be trained using a bounding box with parameters optimized for the convex mirror. The parameters optimized for the convex mirror include the height of the bounding box, the width of the bounding box, the abscissa of the center point of the bounding box, the ordinate of the center point of the bounding box, and the height of the bounding box. Width It may include ratios.

[0062] In an exemplary embodiment, a deep learning approach is used to recognize convex mirrors. Instead of using a normal default box for model training, the machine learning model may use an optimized convex mirror size from the normal default box. The optimal mirror size is identified based on test results of image capture devices, such as cameras, detecting convex mirrors on public roads. The optimal mirror size may depend on factors such as the resolution of the camera used. Therefore, in various exemplary embodiments, the mirror size may be adjusted and optimized accordingly. In the exemplary embodiment shown in FIG. 11, the optimal mirror size is approximately 0.2 times the overall image size. Compared to the traditional use of a normal default box, adopting the optimized convex mirror size enables convex mirror detection from a longer distance. In an exemplary embodiment, using the optimized convex mirror size achieves a faster detection time of 21.5 milliseconds (ms) while maintaining a comparable accuracy level. An example of a machine learning model may be a Single Shot Multibox Detector (SSD).

[0063] [Table 2]

[0064] In an exemplary implementation using optimized convex mirror sizes, first, intersections are detected by an image capture device, i.e., a camera. Optionally, map information may be useful. For example, map information may be provided and matched against Global Positioning System (GPS) coordinates to identify intersections or junctions. Then, a machine learning algorithm is applied at the intersections to identify / detect convex mirror areas.

[0065] In an exemplary embodiment, YOLOv3 is described as a real-time detection system for detecting traffic mirror candidates. YOLOv3 is a real-time object detection system that applies a single neural network to the entire image. The network divides the image into regions and predicts bounding boxes and probabilities for each region. These bounding boxes are weighted by the predicted probabilities. The YOLOv3 system offers several advantages over classifier-based systems. Because it looks at the entire image at test time, predictions are typically based on the global context within the image. It also makes predictions with a single network evaluation, unlike systems like R-CNN, which require thousands per image. This makes it extremely fast, over 1000 times faster than R-CNN and 100 times faster than Fast R-CNN. Additional information about YOLOv3 can be found in [Non-Patent Document 1], which is incorporated herein by reference. Examples of YOLOv3 can be found in [Non-Patent Document 2], which is incorporated herein by reference, examples of YOLOv3 architecture can be found at least in Section 3.2.1 and Figure 2, and examples of YOLOv3 training can be found at least in Section 4.2.

[0066] A first example of a dataset that can be used to train the YOLOv3 machine learning model is the COCO dataset, which is a large-scale object detection, segmentation, and captioning dataset available at https: / / cocodataset.org / #home. A second example of a dataset that can be used to train the YOLOv3 machine learning model is the CIFAR-10 or CIFAR-100 dataset, which is a labeled subset of a small 80 million image dataset available at http: / / www.cs.toronto.edu / ~kriz / cifar.html. It is contemplated that any other suitable dataset can be used.

[0067] In an exemplary embodiment, the DAGMM is used as an anomaly detection algorithm to determine whether a candidate convex mirror is a convex mirror. The DAGMM utilizes a deep autoencoder to generate a low-dimensional representation and reconstruction error for each input data point, which are then fed into a Gaussian Mixture Model (GMM). Instead of using separate two-stage training and the standard Expectation-Maximization (EM) algorithm, the DAGMM jointly optimizes the deep autoencoder parameters and the mixture model end-to-end, and uses a separate estimation network to facilitate parameter learning for the mixture model. The joint optimization, which successfully balances autoencoder reconstruction, density estimation of the latent representation, and regularization, helps the autoencoder avoid less attractive local optima and further reduce the reconstruction error, eliminating the need for pre-training. Additional information regarding the DAGMM can be found in [Non-Patent Document 3], which is incorporated herein by reference.

[0068] One example of a dataset that can be used to train a DAGMM machine learning model is the KDDCUP99 10 percent dataset from the UCI repository, available at https: / / archive.ics.uci.edu / ml / datasets / KDD+Cup+1999+Data. It is contemplated that any other suitable dataset can be used.

[0069] The exemplary embodiment described above was validated using a front camera mounted on a vehicle in a feasibility study, and the effectiveness of the method was demonstrated by experimental results on public roads.

[0070] The above-described exemplary embodiments advantageously can detect convex mirrors that are depicted as perfect circles, as well as convex mirrors that are depicted as ellipses from the viewing angle of the image capture device, in contrast to existing ADAS that typically cannot detect convex mirrors when the convex mirror appears as an ellipse from the viewing angle of the image capture device.

[0071] The above-described exemplary embodiments can advantageously reduce the occurrence of false positive results and improve the accuracy of convex mirror detection compared to approaches that use only known deep learning models, in contrast to existing detection systems that incorrectly identify road traffic signs as convex mirrors.

[0072] The exemplary embodiments described above can advantageously provide faster computations and beneficially save time compared to approaches that use only known deep learning models.

[0073] The exemplary embodiments described above may be used for collision prediction and collision avoidance, for example, at road locations with blind spots and at intersections without traffic lights.

[0074] The exemplary embodiments described above may advantageously reduce the investment required to build new facilities at intersections and low visibility locations by utilizing a piece of conventional infrastructure already present on roadways: road safety mirrors.

[0075] The exemplary embodiments described above may be advantageously used to support Level 1 and 2 Autonomous Driving (AD) systems, such as Advanced Driver Assistance Systems (ADAS), and may be further extended to support Level 3 and above AD systems. The exemplary embodiments described above may also be advantageously applied in other forms of vehicles, such as unmanned ground vehicles (uGVs), automated guided vehicles (AGVs), autonomous vehicles, drones, etc. The exemplary embodiments described above may further advantageously be used in the field of robotics.

[0076] The terms "coupled" or "connected," as used in this description, are intended to cover both direct connections and connections through one or more intermediary means, unless expressly stated otherwise.

[0077] Terms such as "configured to perform (a task / operation)", "configured for performing (a task / operation)", etc., as used in this description, include being programmable, programmed, connectable, wired, or otherwise configured to have the capability to perform the task / operation when arranged or installed as described herein. Terms such as "configured to perform (a task / operation)", "configured to perform (a task / operation)", etc., are intended to cover "when used, the task / operation is performed", e.g., specifically performing or performing the task / operation and / or being specifically configured and / or specifically arranged and / or being specifically made to do so.

[0078] The term "and / or," e.g., "X and / or Y," should be understood to mean either "X and Y" or "X or Y," and should not be understood as expressly endorsing either or both meanings.

[0079] The terms "associated with," "related to," and the like, when used herein to refer to two elements, refer to a broad relationship between the two elements. This relationship includes, but is not limited to, a physical, chemical, or biological relationship. For example, if element A is associated with element B, elements A and B may be directly or indirectly attached to each other, or element A contains element B, or vice versa.

[0080] Terms such as "exemplary embodiment," "exemplary implementation," "exemplary," and the like, as used herein, are intended to indicate an example of the subject matter described in this disclosure. Such an example may relate to one or more features defined in the claims, and is not necessarily intended to highlight the best example or any fundamental importance of any feature.

[0081] Certain portions of this specification may be explicitly or implicitly described in terms of algorithms and / or functional operations performed on data within a computer memory or electronic circuitry. These algorithmic descriptions and / or functional operations are typically used by those skilled in the information processing arts for efficient description. An algorithm generally relates to a self-consistent sequence of steps leading to a desired result. The steps of an algorithm may include physical manipulations of physical quantities, such as electrical, magnetic, or optical signals capable of being stored, sent, transmitted, combined, compared, and otherwise manipulated.

[0082] Furthermore, unless expressly stated otherwise, and as will generally be apparent from the following, those skilled in the art will understand that throughout this specification discussions utilizing terms such as "scan," "calculate," "identify," "replace," "generate," "initialize," "output," and the like refer to operations and processes of an instruction processor / computer system or similar electronic circuit / device / component that manipulate / process data represented as physical quantities within the described system and convert it into other data similarly represented as physical quantities in that system or other information storage, transmission, or display device, etc.

[0083] This description also discloses devices / apparatus associated with performing the method steps described above. Such apparatus may be specially configured for the purposes of the method, or may include a general-purpose computer / processor or other device selectively activated or reconfigured by a computer program stored in a memory member. The algorithms and displays described herein are not inherently related to any particular computer or other apparatus. It will be understood that a general-purpose device / machine may be used in accordance with the teachings herein. Alternatively, the construction of a specialized device / apparatus to perform the method steps may be desired.

[0084] In addition, the description is also proposed to implicitly cover computer programs, in that it is clear that the steps of the methods described herein may be embodied by computer code. It will be appreciated that a variety of programming languages ​​and encodings can be used to implement the teachings of the description herein. Furthermore, the computer program, where applicable, is not limited to any particular control flow, and different control flows may be used without departing from the scope of the present invention.

[0085] Furthermore, one or more of the steps of the computer program may be executed in parallel and / or sequentially, where applicable. Such a computer program may be stored on any computer-readable medium, where applicable. The computer-readable medium may include storage devices such as magnetic or optical disks, memory chips, or other storage devices suitable for interfacing with an appropriate reader / general-purpose computer. In such cases, the computer-readable storage medium is non-transitory. Such storage media also encompasses any computer-readable medium, e.g., storing data only for a short time and / or only when power is present, such as register memory, processor cache, and random access memory (RAM), among others. The computer-readable medium may also include wired media, as exemplified in the Internet system, or wireless media, as exemplified by Bluetooth technology. The computer-readable medium may be, for example, cloud storage on the Internet or within an intranet. When the computer program is loaded into an appropriate reader and executed thereon, the result is effectively an apparatus capable of implementing, for example, in a physical embodiment, the steps of the aforementioned method. The computer readable medium is intended to be transportable and reproducible in the sense that the computer program, if applicable, is reproducible.

[0086] The exemplary embodiments may also be implemented as hardware modules. A module is a functional hardware unit designed for use with other components or modules. For example, a module may be implemented using digital or discrete electronic components, or may form part of an entire electronic circuit, such as an Application Specific Integrated Circuit (ASIC). Those skilled in the art will appreciate that the exemplary embodiments may also be implemented as a combination of hardware and software modules.

[0087] Additionally, in describing some embodiments, the present disclosure may disclose methods and / or processes as a particular sequence of steps. However, unless otherwise required, it should be understood that the method or process should not be limited to the particular sequence of steps disclosed. Other sequences of steps may be possible. The particular order of steps disclosed herein should not be construed as an undue limitation. Unless otherwise required, the methods and / or processes disclosed herein should not be limited to performing the steps in the order described. The sequence of steps may be varied and still remain within the scope of the present disclosure.

[0088] Furthermore, within the description herein, whenever the term "substantially" is used, it should be understood to include, but not be limited to, terms such as "entirely" or "completely." Additionally, whenever used, terms such as "comprising" are intended to be open-ended descriptive language in that they broadly include the elements / components listed following the term, as well as other components not explicitly listed. For example, when "comprising" is used, a reference to "one" feature is also intended to refer to "at least one" of that feature. Terms such as "consisting" may, in appropriate context, be considered subsets of terms such as "comprising." Accordingly, where embodiments are disclosed herein using terms such as "comprising," it should be understood that these embodiments also provide teachings regarding corresponding embodiments using terms such as "consisting." Additionally, terms such as "about," "approximately," and the like, whenever used, typically refer to a reasonable variation, such as a + / - 5% variation from the disclosed value, or a 4% variation from the disclosed value, or a 3% variation from the disclosed value, or a 2% variation from the disclosed value, or a 1% variation from the disclosed value.

[0089] Furthermore, within the description herein, certain values ​​may be disclosed in ranges. The endpoints of a range are intended to exemplify the preferred range. Whenever a range is described, it is intended that the range cover and teach all individual values ​​within the range, as well as all possible subdivisions. That is, the endpoints of a range should not be construed as indeterminate limits. For example, a description of a range of 1% to 5% is intended to specifically disclose individual values ​​within the range, e.g., 1%, 2%, 3%, 4%, 5%, as well as subdivisions such as 1% to 2%, 1% to 3%, 1% to 4%, 2% to 3%, etc. The specific disclosure of the recitation applies to any depth / width of a range.

[0090] Various exemplary embodiments may be implemented in terms of data structures, program modules, programs, and computer instructions executed in a computer-implemented environment. A specially configured general-purpose computing environment is briefly disclosed herein. One or more exemplary embodiments may be embodied in one or more computer systems, such as, for example, the one shown generally in FIG. 12.

[0091] One or more exemplary embodiments may be implemented as software, for example, as a computer program executing within computer system 1200 and instructing computer system 1200 to perform the methods of the exemplary embodiments.

[0092] The computer system 1200 includes a computer unit 1202, input modules such as a keyboard 1204 and a pointing device 1206, and multiple output devices such as a display 1208 and a printer 1210. A user can interact with the computer unit 1202 using the devices described above. The pointing device can be implemented as a mouse, a trackball, a pen device, or any similar device. One or more other input devices (not shown), such as a joystick, a gamepad, a satellite dish, a scanner, a touch-sensitive screen, etc., can also be connected to the computer unit 1202. The display 1208 can include a cathode ray tube (CRT), a liquid crystal display (LCD), a field emission display (FED), a plasma display, or any other device that generates images viewable by a user.

[0093] The computer unit 1202 can be connected to a computer network 1212 via an appropriate transceiver device 1214, thereby providing access to the Internet or other network systems, such as a Local Area Network (LAN) or Wide Area Network (WAN) or a personal network. The network 1212 can include servers, routers, networked personal computers, peer devices or other common network nodes, wireless telephones or wireless personal digital assistants. Networking environments can be found in offices, company-wide computer networks, home computer systems, and the like. The transceiver device 1214 can be a modem / router unit within the computer unit 1202 or external to it, and can be any type of modem / router, such as a cable modem or satellite modem.

[0094] It should be understood that the illustrated network connections are exemplary and that other methods of establishing a communications link between the computers may be used. Any of a variety of protocols may be assumed to be present, such as TCP / IP, Frame Relay, Ethernet, FTP, HTTP, etc., and the computer unit 1202 may operate in a client-server configuration to allow users to retrieve web pages from a web-based server. Additionally, any of a variety of web browsers may be used to display and manipulate data on the web pages.

[0095] The computer unit 1202 in this example includes a processor 1218, random access memory (RAM) 1220, and read only memory (ROM). The ROM 1222 may be system memory that stores basic input / output system (BIOS) information. The RAM 1220 may store one or more program modules, such as an operating system, application programs, and program data.

[0096] The computer unit 1202 further includes a number of input / output (I / O) interface units, such as an I / O interface unit 1224 with the display 1208 and an interface unit 1226 with the keyboard 1204. The components of the computer unit 1202 are typically connected and communicate and interfaced / coupled via an interconnected system bus 1228 and in a manner known to those skilled in the relevant art. The bus 1228 can be any of several types of bus structures including a memory bus or memory controller, a peripheral bus, and a local bus using any of a variety of bus architectures.

[0097] It should be understood that other devices can also be connected to the system bus 1228. For example, a video or digital camera can be coupled to the system bus 1228 using a Universal Serial Bus (USB) interface. An IEEE 1394 interface can be used to couple additional devices to the computer unit 1202. Other manufacturers' interfaces can also be used, such as FireWire developed by Apple Computer or i.Link developed by Sony. Devices can also be coupled to the system bus 1228 via a parallel port, game port, PCI board, or any other interface used to couple input devices to a computer. It should also be understood that, although components not shown, a microphone and speakers can be used to record and play back voice / audio. A sound card can be used to couple the microphone and speakers to the system bus 1228. It should be understood that several peripheral devices can be simultaneously coupled to the system bus 1228 via alternative interfaces.

[0098] The application program may be provided to a user of the computer system 1200 in a form encoded / stored on a data storage medium, such as a CD-ROM or flash memory carrier. The application program may be readable using a corresponding data storage medium drive of the data storage device 1230. The data storage medium is not limited to being portable and may include an example embedded within the computer unit 1202. The data storage device 1230 may include a hard disk interface unit and / or a removable memory interface unit (neither of which are shown in detail), which couples a hard disk drive and / or a removable memory drive, respectively, to the system bus 1228, thereby enabling data to be read from and written to the drive. Examples of removable memory drives include magnetic disk drives and optical disk drives. Drives and their associated computer-readable media, such as floppy disks, provide non-volatile storage of computer-readable instructions, data structures, program modules, and other data for the computer unit 1202. It is understood that the computer unit 1202 may include more than one such drive. Additionally, the computer unit 1202 may include drives for interfacing with other types of computer-readable media.

[0099] Application programs are read and controlled by execution by processor 1218. Intermediate storage of program data may be provided using RAM 1220. The methods of the exemplary embodiments may be implemented as computer-readable instructions, computer-executable components, or software modules. One or more software modules may alternatively be used. These may include executable programs, data link libraries, configuration files, databases, graphic images, binary data files, text data files, object files, source code files, or the like. When one or more computer processors execute one or more of the software modules, the software modules interact to cause one or more computer systems to operate in accordance with the teachings herein.

[0100] The operation of the computer unit 1202 can be controlled by various program modules. Examples of program modules are routines, programs, objects, components, data structures, libraries, etc. that perform particular tasks or implement particular abstract data types. The exemplary embodiments may also be implemented with other computer system configurations, including handheld devices, multiprocessor systems, microprocessor-based or programmable consumer electronics, network PCs, minicomputers, mainframe computers, personal digital assistants, mobile phones, etc. Moreover, the exemplary embodiments may also be implemented in distributed computing environments where tasks are performed by remote processing devices that are linked through a wireless or wired communications network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

[0101] The exemplary embodiments may also be implemented with other computer system configurations, including handheld devices, multiprocessor systems / servers, microprocessor-based or programmable consumer electronics, network PCs, minicomputers, mainframe computers, personal digital assistants, mobile phones, etc. Moreover, the exemplary embodiments may also be implemented in distributed computing environments where tasks are performed by remote processing devices that are linked through a wireless or wired communications network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

[0102] In the foregoing exemplary embodiments, a vehicle may be described as an automobile driven by a user. It should be understood that the exemplary embodiments are not so limited. For example, a vehicle may include any movable object capable of detecting a convex mirror.

[0103] Those skilled in the art will recognize that various modifications and / or improvements may be made to the particular embodiments without departing from the scope of the present invention, as broadly described. For example, within the description herein, features of different exemplary embodiments may be mixed, combined, exchanged, incorporated, adopted, improved, included, etc., among the different exemplary embodiments. For example, exemplary embodiments are not necessarily mutually exclusive, as some may be combined with one or more embodiments to form new exemplary embodiments. Furthermore, although the present disclosure provides embodiments having one or more of the features / characteristics discussed herein, one or more of these features / characteristics may also be surrendered in other alternative embodiments, and the present disclosure supports such surrenders and related alternative embodiments. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive. The present application relates to the invention described in the claims, but also includes the following as other aspects. 1. A computer-implemented method for detecting a convex mirror (814) in an image (802), comprising: applying a machine learning algorithm to the image (802) to identify potential convex mirrors (800) in the image (802); applying an anomaly detection algorithm to the identified convex mirror candidate (800) to determine whether the convex mirror candidate (800) is a convex mirror (814); 10. A computer-implemented method comprising: 2. The anomaly detection algorithm is Deep Autoencoder Gaussian The method described in 1 above is based on the Mixture Model (DAGMM). 3. 3. The method according to claim 1 or 2, wherein the convex mirror candidate (800) is confirmed as a convex mirror (814) if it cannot be a traffic sign (820). 4. The anomaly detection algorithm applying an autoencoder function to image data associated with the convex mirror candidate (800) to obtain points (808, 810) on a transformation map (812), the points (808, 810) representing the convex mirror candidate (800) on the transformation map (812); confirming the convex mirror candidate (800) as a convex mirror (814) if the point (808, 810) is greater than a threshold distance from a cluster (816, 818) representing a traffic sign (820) on the transformation map (812); 4. The method according to any one of 1 to 3 above, comprising: 5. 5. The method of claim 4, wherein there are multiple clusters (816, 818) representing traffic signs (820), and the convex mirror candidate (800) is confirmed to be a convex mirror (814) if the point (808, 810) is beyond a threshold distance from each of the clusters (816, 818). 6. 6. The method according to any one of 1 to 5 above, wherein the machine learning algorithm is trained using a bounding box with parameters optimized for convex mirrors. 7. The parameters optimized for the convex mirror include the height of a bounding box, the width of the bounding box, the abscissa of the center point of the bounding box, the ordinate of the center point of the bounding box, and the ratio of the height of the bounding box to the Width 7. The method of claim 6, comprising the ratio 8. 8. The method according to any one of 1 to 7 above, further comprising the step of acquiring the image (802) using an image capture device (102). 9. 9. The method of claim 8, wherein said step of acquiring said image (802) comprises acquiring a plurality of images over different time instances. 10. 10. The method according to any one of 1 to 9 above, wherein the image is a real-time image. 11. A system (100) for detecting a convex mirror (814) in an image (802), comprising: an image capture device (102); an electronic control unit (104) coupled to the image capture device (102); Including, the image capture device (102) is configured to acquire the image (802); The electronic control unit (104) is configured to apply a machine learning algorithm to the image (802) to identify convex mirror candidates (800) in the image (802), and to apply an anomaly detection algorithm to the identified convex mirror candidates (800) to determine whether the convex mirror candidates (800) are convex mirrors (814). A system characterized by: 12. The anomaly detection algorithm is Deep Autoencoder Gaussian 12. The system according to claim 11, based on the Mixture Model (DAGMM). 13. 13. The system according to claim 11 or 12, wherein the convex mirror candidate (800) is confirmed as a convex mirror (814) if it cannot be a traffic sign (820). 14. The anomaly detection algorithm applying an autoencoder function to image data associated with the convex mirror candidate (800) to obtain points (808, 810) on a transformation map (812), the points (808, 810) representing the convex mirror candidate (800) on the transformation map (812); confirming the convex mirror candidate (800) as a convex mirror (814) if the point (808, 810) is greater than a threshold distance from a cluster (816, 818) representing a traffic sign (820) on the transformation map (812); 14. The system according to any one of the above 11 to 13, comprising: 15. 1. A computer-readable storage medium having stored thereon instructions for instructing a processing unit of a system to perform a computer-implemented method for detecting convex mirrors (814) in an image (802), the method comprising: applying a machine learning algorithm to the image (802) to identify potential convex mirrors (800) in the image (802); applying an anomaly detection algorithm to the identified convex mirror candidate (800) to determine whether the convex mirror candidate (800) is a convex mirror (814); 1. A computer-readable storage medium comprising: [Explanation of symbols]

[0104] 100 System for detecting convex mirrors in an image 102 Image capture device 104 Processing Unit 106 Object Detection Unit 108 Operating Unit 302 slots 402 slots 404 frames 700 Conversion Map 702a First Data Point 702b First Traffic Sign 704a Second Data Point 704b Second Traffic Sign Cluster of 706 data points 706 First Convex Mirror 708 Second Convex Mirror 800 Convex mirror candidate 802 images 804 frames 806 frames 808 data points 810 data points 812 Conversion Map 814 Convex Mirror Cluster of 816 data points A cluster of 818 data points 820 traffic sign 1000 vehicles 1002 frames 1004 frames 1200 Computer System 1202 Computer Unit 1204 keyboard 1206 Pointing Device 1208 Display 1210 Printer 1212 Computer Network 1214 Transceiver Device 1218 processor 1220 Random Access Memory 1222 Read-Only Memory 1224 Input / Output Interface Unit 1226 Interface Unit 1228 System Bus 1230 Data Storage Device

Claims

1. 1. A computer-implemented method for detecting a convex mirror (814) in an image (802), comprising: applying a machine learning algorithm to the image (802) to identify potential convex mirrors (800) in the image (802); applying an anomaly detection algorithm to the identified convex mirror candidate (800) to determine whether the convex mirror candidate (800) is a convex mirror (814); Including, The convex mirror candidate (800) is confirmed as a convex mirror (814) if it cannot be a traffic sign (820); The anomaly detection algorithm applying an autoencoder function to image data associated with the convex mirror candidate (800) to obtain points (808, 810) on a transformation map (812), the points (808, 810) representing the convex mirror candidate (800) on the transformation map (812); confirming the convex mirror candidate (800) as a convex mirror (814) if the point (808, 810) is located more than a threshold distance away from a cluster (816, 818) representing a traffic sign (820) on the transformation map (812); Including, 10. A computer-implemented method comprising:

2. The method of claim 1 , wherein the anomaly detection algorithm is based on a Deep Autoencoder Gaussian Mixture Model (DAGMM).

3. 3. The method of claim 1, wherein there are multiple clusters (816, 818) representing traffic signs (820), and the candidate convex mirror (800) is confirmed to be a convex mirror (814) if the point (808, 810) is more than a threshold distance away from each of the clusters (816, 818).

4. The method of claim 1 or 2, wherein the machine learning algorithm is trained using bounding boxes with parameters optimized for convex mirrors.

5. 5. The method of claim 4, wherein the parameters optimized for the convex mirror include a height of a bounding box, a width of the bounding box, an abscissa of a center point of the bounding box, an ordinate of the center point of the bounding box, and a height-to-width ratio of the bounding box.

6. The method of claim 1 or 2, further comprising acquiring the image (802) using an image capture device (102).

7. The method of claim 6 , wherein acquiring the image (802) comprises acquiring multiple images over different time instances.

8. The method of claim 1 or 2, wherein the image is a real-time image.

9. A system (100) for detecting a convex mirror (814) in an image (802), comprising: an image capture device (102); an electronic control unit (104) coupled to the image capture device (102); Including, the image capture device (102) is configured to acquire the image (802); The electronic control unit (104) is configured to apply a machine learning algorithm to the image (802) to identify convex mirror candidates (800) in the image (802), and to apply an anomaly detection algorithm to the identified convex mirror candidates (800) to determine whether the convex mirror candidates (800) are convex mirrors (814); The convex mirror candidate (800) is confirmed as a convex mirror (814) if it cannot be a traffic sign (820); The anomaly detection algorithm applying an autoencoder function to image data associated with the convex mirror candidate (800) to obtain points (808, 810) on a transformation map (812), the points (808, 810) representing the convex mirror candidate (800) on the transformation map (812); confirming the convex mirror candidate (800) as a convex mirror (814) if the point (808, 810) is located more than a threshold distance away from a cluster (816, 818) representing a traffic sign (820) on the transformation map (812); Including, A system characterized by:

10. The system of claim 9 , wherein the anomaly detection algorithm is based on a Deep Autoencoder Gaussian Mixture Model (DAGMM).

11. 1. A computer-readable storage medium having stored thereon instructions for instructing a processing unit of a system to perform a computer-implemented method for detecting convex mirrors (814) in an image (802), the method comprising: applying a machine learning algorithm to the image (802) to identify potential convex mirrors (800) in the image (802); applying an anomaly detection algorithm to the identified convex mirror candidate (800) to determine whether the convex mirror candidate (800) is a convex mirror (814); Including, The convex mirror candidate (800) is confirmed as a convex mirror (814) if it cannot be a traffic sign (820); The anomaly detection algorithm applying an autoencoder function to image data associated with the convex mirror candidate (800) to obtain points (808, 810) on a transformation map (812), the points (808, 810) representing the convex mirror candidate (800) on the transformation map (812); confirming the convex mirror candidate (800) as a convex mirror (814) if the point (808, 810) is located more than a threshold distance away from a cluster (816, 818) representing a traffic sign (820) on the transformation map (812); Including, A computer-readable storage medium comprising:

Images