Intel Corporation

Nec (china) Co., Ltd.

Shaopeng Tang

Yurong Chen

Anbang Yao

Feng Wang

Wei Zeng

Guoyi Liu

Hongming Zhang

Lei Qin

Qingyuan Wang

Qingming Huang

Techniques are provided for recognition of activity in a sequence of video image frames that include depth information. A methodology embodying the techniques includes segmenting each of the received image frames into a multiple windows and generating spatio-temporal image cells from groupings of windows from a selected sub-sequence of the frames. The method also includes calculating a four dimensional (4D) optical flow vector for each of the pixels of each of the image cells and calculating a three dimensional (3D) angular representation from each of the optical flow vectors. The method further includes generating a classification feature for each of the image cells based on a histogram of the 3D angular representations of the pixels in that image cell. The classification features are then provided to a recognition classifier configured to recognize the type of activity depicted in the video sequence, based on the generated classification features.

Recognition of activity in a video image sequence using depth information

The present disclosure describes a non-learning based process and apparatus for detecting humans in an image. This may include receiving an image that has pixel distance information from a camera and using that to determine a height of the pixel above a ground surface. One or more regions may then be identified that may include a head and shoulders of an individual in the image. A multiple threshold technique may be used to remove some background regions, and a mean-shift technique used to find the local highest regions that may be combination of head and shoulders of the person. In embodiments, the view angle and/or the height of the camera may not be fixed.

Human detection in high density crowds

A method and a device for objects counting in image processing includes acquiring the depth image of any one frame; detecting objects according to the depth image; associating the identical object in different frames to form a trajectory; and determining the number of objects according to the number of trajectories. The devices include an acquisition module for acquiring the depth image of any one frame; a detection module for detecting objects according to the depth image; an association module for associating the identical object in different frames to form a trajectory; a determining module for determining the number of objects according to the number of trajectories. The objects are detected according to the depth image. The identical object in different frames is associated to form a trajectory and the number of objects is determined according to the number of trajectories.

Method and a device for objects counting

A method and device for extracting color features, relating to the field of image processing includes converting an original image into sub-images corresponding to channels in a color space, dividing the sub-images into a plurality of cells with identical size, and calculating the color histograms of each of the plurality of cells. A cell and neighboring cells thereof are defined as the effective scope of the cell, and a feature vector of the cell is determined according to a degree of similarity of the color histograms of every two neighboring cells in the effective scope. The feature vectors of the cells in the sub-images are concatenated to obtain feature vectors of the sub-images, and a feature vector of the original image is obtained according to the feature vectors of the sub-images.

Method and a device for extracting color features

Growing community of inventors

Beijing, China

Shaopeng Tang