A method of controlling an image acquisition device for tracking a target object includes: detecting an event in which tracking of a first object, which is a tracking target object, fails in a first image acquired by the image acquisition device; determining, in the first image, a reference object which is used as a reference for controlling the image acquisition device; controlling the image acquisition device such that at least one of an image capturing range and an image capturing direction of the image acquisition device is adjusted based on at least one of a size and a location of the reference object in the first image; and recognizing the first object in a second image acquired by the image acquisition device in a state in which at least one of the image capturing range and the image capturing direction is adjusted.

A human-object interaction detection method, a neural network and a training method therefor is provided. The human-object interaction detection method includes: extracting a plurality of first target features and one or more first motion features from an image feature of an image to be detected; fusing each first target feature and some of the first motion features to obtain enhanced first target features; fusing each first motion feature and some of the first target features to obtain enhanced first motion features; processing the enhanced first target features to obtain target information of a plurality of targets including human targets and object targets; processing the enhanced first motion features to obtain motion information of one or more motions, where each motion is associated with one human target and one object target; and matching the plurality of targets with the one or more motions to obtain a human-object interaction detection result.

Broadly speaking, the present techniques generally relate to a method and apparatus for video recognition, and in particular relate to a computer-implemented method for performing video recognition using a transformer-based machine learning, ML, model. Put another way, the present techniques provide new methods of image processing in order to automatically extract feature information from a video.

There is provided a computer implemented method of extracting information about a person. Incoming sensor signals for monitoring people within a field of view of a sensor system are received and processed. In response to detecting a person located within a notification region, an output device outputs a notification to the detected person. Processing of the incoming sensor signals continues in order to monitor behaviour patterns of the person and determine from his behaviour patterns whether he is currently in a consenting or non-consenting state. An extraction function attempts to extract information about the person irrespective of his determined state. A sharing function determines whether or not to share an extracted piece of information about the person with a receiving entity in accordance with his determined state, the information not being shared unless and until it is subsequently determined that the person is in the consenting state.

A queue analysis apparatus (2000) estimates a position and an orientation of each object (20) included in a target image (10). The target image (10) is generated by a camera (50) that captures the object (20). The queue analysis apparatus (2000) generates a queue line (40) that expresses, by a linear shape, a queue included in a queue region (30) being a region representing a queue in the target image (10), based on a position and an orientation being estimated for each object (20) included in the queue region (30).

A queue analysis apparatus (2000) estimates a position and an orientation of each object (20) included in a target image (10). The target image (10) is generated by a camera (50) that captures the object (20). The queue analysis apparatus (2000) generates a queue line (40) that expresses, by a linear shape, a queue included in a queue region (30) being a region representing a queue in the target image (10), based on a position and an orientation being estimated for each object (20) included in the queue region (30).

This application relates to systems, methods, devices, and other techniques that can be utilized to simulate and analyze behaviors of customers in a retail environment.

A method and a device for determining a placement region of an item are disclosed. The method according to the present disclosure comprises: acquiring position information of an electronic identification at a bar display screen; and determining the placement region of the item according to the position information and a preset mapping relationship.

Provided are a device and a method which enable easy analysis and evaluation of work efficiency of a worker without burdensome tasks and easy determination of a worker's skill level by comparing the worker's work efficiency status with that of another worker or a past record of the same worker, wherein analytical information is produced by estimating the worker's joint positions based on a video; acquiring time series data on joint positions; determining work efficiency based on the time series data; acquiring a target range (part of a work process with low work efficiency); output an image of the target range overlaid on a graph of the time series data; and output a posture image of the worker overlaid on the video. The analytical information may include information on a working activity to be analyzed and information on a chosen model working activity with high work efficiency.

A behavior recognition method and system, including: dividing video data into a plurality of video clips, performing frame extraction processing on each video clip to obtain frame images, and performing optical flow extraction on the frame images to obtain optical flow images; performing feature extraction on the frame images and the optical flow images to obtain feature maps of the frame images and the optical flow images; performing spatio-temporal convolution processing on the feature maps of the frame images and the optical flow images, and determining a spatial prediction result and a temporal prediction result; fusing the spatial prediction results of all the video clips to obtain a spatial fusion result, and fusing the temporal prediction results of all the video clips to obtain a temporal fusion result; and performing two-stream fusion on the spatial fusion result and the temporal fusion result to obtain a behavior recognition result.