Abstract: Disclosed are methods, systems, and apparatus for adjusting areas of interest for motion detection in camera scenes. A method includes obtaining a map of false motion event detections using a first area of interest; identifying an overlap area between the map of false detections and the first area of interest; determining a second area of interest that includes portions of the first area of interest and excludes at least a part of the overlap area; obtaining a map of true motion event detections using the first area of interest; determining whether true detections using the second area of interest compared to true detections using the first area of interest satisfies performance criteria; and in response to determining that true detections using the second area of interest compared to true detections using the first area of interest satisfies performance criteria, providing the second area of interest for use in detecting events.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving multiple images from a camera, each image of the multiple images representative of a detection of an object within the image. For each image of the multiple images the methods include: determining a set of detected objects within the image, each object defined by a respective bounding box, and determining, from the set of detected objects within the image and ground truth labels, a false detection of a first object. The methods further include determining that a target object threshold is met based on a number of false detections of the first object in the multiple images, generating, based on the number of false detections for the first object meeting the target object threshold, an adversarial mask for the first object, and providing, to the camera, the adversarial mask.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for false detection removal using adversarial masks. The method includes performing object detection on a first image that includes a first region using a detection model determining the detection model incorrectly classified the first region of the first image; generating an adversarial mask based on the first region of the first image and the detection model; obtaining a second image that includes the first region; generating a masked image based on the second image and the adversarial mask; and performing object detection on the masked image including the first region using the detection model.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for Object Embedded Learning. One of the methods includes maintaining data that represents an image; providing, to a machine learning model, the data that represents the image; receiving, from the machine learning model, output data that includes i) an object detection result that indicates whether a target object is detected in the image and ii) an object embedding for the target object; and determining whether to perform an automated action using the output data.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for spatial motion attention for intelligent video analytics. One of the methods includes: obtaining an input image of a region; generating a motion image that characterizes a difference between a value of a pixel at the pixel location in the input image and a value of a pixel at the pixel location in the reference image; generating a feature map using the input image; generating, using the motion image and the feature map, a motion enhanced feature map that has, for one or more pixels that likely indicate movement, a first value that a) indicates that the corresponding pixel in the motion enhanced feature map likely indicates movement and b) is different from a second value for a corresponding pixel in the feature map; and analyzing the motion enhanced feature map.

Abstract: Disclosed are methods, systems, and apparatus for adjusting areas of interest for motion detection in camera scenes. A method includes obtaining a map of false motion event detections using a first area of interest; identifying an overlap area between the map of false detections and the first area of interest; determining a second area of interest that includes portions of the first area of interest and excludes at least a part of the overlap area; obtaining a map of true motion event detections using the first area of interest; determining whether true detections using the second area of interest compared to true detections using the first area of interest satisfies performance criteria; and in response to determining that true detections using the second area of interest compared to true detections using the first area of interest satisfies performance criteria, providing the second area of interest for use in detecting events.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving multiple images from a camera, each image of the multiple images representative of a detection of an object within the image. For each image of the multiple images the methods include: determining a set of detected objects within the image, each object defined by a respective bounding box, and determining, from the set of detected objects within the image and ground truth labels, a false detection of a first object. The methods further include determining that a target object threshold is met based on a number of false detections of the first object in the multiple images, generating, based on the number of false detections for the first object meeting the target object threshold, an adversarial mask for the first object, and providing, to the camera, the adversarial mask.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for false detection removal using adversarial masks. The method includes performing object detection on a first image that includes a first region using a detection model determining the detection model incorrectly classified the first region of the first image; generating an adversarial mask based on the first region of the first image and the detection model; obtaining a second image that includes the first region; generating a masked image based on the second image and the adversarial mask; and performing object detection on the masked image including the first region using the detection model.