Disclosed herein are systems, methods, and devices for detecting traffic lane violations. In one embodiment, a method for detecting a potential traffic violation is disclosed comprising bounding a vehicle detected from one or more video frames of a video in a vehicle bounding box. The vehicle can be detected and bounded using a first convolutional neural network. The method can also comprise bounding, using the one or more processors of the edge device, a plurality of lanes of a roadway detected from the one or more video frames in a plurality of polygons. The plurality of lanes can be detected and bounded using multiple heads of a multi-headed second convolutional neural network. The method can further comprise detecting a potential traffic violation based in part on an overlap of at least part of the vehicle bounding box and at least part of one of the polygons.

According to an embodiment, a captured image check system includes a camera, an image data input unit, a camera view angle judge processor, a road surface state analysis judge processor, and an output unit. The camera photographs a road surface. The image data input unit inputs image data to be used for analyzing a state of the road surface. The camera view angle judge processor performs a judge process of determining whether or not an angle of view of the camera satisfies a first condition for analyzing the state of the road surface on the basis of the image data. The road surface state analysis judge processor performs a judge process of determining whether or not a second condition for analyzing the state of the road surface is satisfied on the basis of image data of the road surface. The output unit outputs results of the judge processes.

A computing device for handling video content analysis, comprises a preprocessing module, for receiving a first plurality of frames and for determining whether to delete at least one of the first plurality of frames according to an event detection, to generate a second plurality of frames according to the determination for the first plurality of frames; a first deep learning module, for receiving the second plurality of frames and for determining whether to delete at least one of the second plurality of frames according to a plurality of features of the second plurality of frames, to generate a third plurality of frames according to the determination for the second plurality of frames; and a second deep learning module, for receiving the third plurality of frames, to generate a plurality of prediction outputs of the third plurality of frames.

An apparatus for correcting a road region includes a processor configured to segment a road region extracted from an aerial image and representing a road into a plurality of partial road regions; associate, for each of the partial road regions, the partial road region with a road section existing at the location of the partial road region, the road section being indicated by map information indicating locations of respective road sections; and correct the road region so as to cover, for each of the partial road regions, the road section corresponding to the partial road region.

Images of an unknown item picked from a store are processed to produce a cropped image. The cropped image is processed to produce a brightness/perspective corrected image, and the brightness/perspective corrected image is processed to produce a low-resolution final image. Image features of the low-resolution final image are extracted and compared against known item features for known items to identify an item code for a known item.

A platform, device and process for capturing images of the surface of a gaming table and determining the quantity, identity, and arrangement of chips bet at a gaming table. Image data is captured corresponding to the one or more chips positioned in at least one betting area on a gaming surface of the respective gaming table and the data is processed to filter out the background, establish a two dimensional grid of points of interests and corresponding histograms for classifying the one or more chips through identifying a dominant classification of each row in the grid of points of interests.

A lane line tracking method and device are provided. The method can include: projecting a lane line detection result of previous K frames preceding a current frame in a camera coordinate system to a world coordinate system, to obtain a first projection result, wherein K is a positive integer greater than or equal to 1, and the previous K frames are consecutive K frames preceding the current frame; projecting the first projection result of the previous K frames in the world coordinate system to a camera coordinate system of the current frame, to obtain a second projection result; and determining, in the camera coordinate system of the current frame, lane line groups of the current frame, according to lane line groups in the second projection result of the previous K frames.

A method for generating training examples for a product recognition model is disclosed. The method includes capturing images of a product using an array of cameras. A product identifier for the product is associated with each of the images. A bounding box for the product is identified in each of the images. The bounding boxes are smoothed temporally. A segmentation mask for the product is identified in each bounding box. The segmentation masks are optimized to generate an optimized set of segmentation masks. A machine learning model is trained using the optimized set of segmentation masks to recognize an outline of the product. The machine learning model is run to generate a set of further-optimized segmentation masks. The bounding box and further-optimized segmentation masks from each image are stored in a master training set with its product identifier as a training example to be used to train a product recognition model.

A vehicle detection apparatus includes circuitry configured to cut out a region of interest in an image, calculate a composite feature quantity of the region of interest as a whole by dividing the region of interest into a plurality of divided regions, calculating a feature quantity of each of the divided regions, and combining the calculated feature quantities of the respective divided regions together, and perform, on the basis of the calculated composite feature quantity, filtering that discards the region of interest that is determinable as not being a wheel of a vehicle.

An image processing apparatus includes a reading unit configured to read an image of a document and generate image data, a first binarization unit configured to generate binary image data by performing halftone processing on the image data generated by the reading unit, a smoothing unit configured to perform smoothing processing on a character region of the binary image data, a second binarization unit configured to perform binarization processing on the character region having been subjected to the smoothing processing by the smoothing unit, and a character recognition unit configured to perform character recognition processing on the character region having been subjected to the binarization processing by the second binarization unit.