Crsc Communication & Information Group Company Ltd.

Xiangbin Kong

Yang Liu

Bing Li

Chenxing Zhang

Guodong Ni

Zhizhong Shen

Jie Di

Weiming Hu

Disclosed is a method for generating training data based on a deformable Gaussian kernel in a crowd counting system, which includes steps of: finding a set of overlapping Gaussian kernels from training data; stretching an occluded Gaussian kernel; rotating the occluded Gaussian kernel; adjusting a center point coordinate of the occluded Gaussian kernel; and determining whether there is any Gaussian kernel that have not been selected yet in the training data, and outputting a resulted crowd density map having gray values as training data. Therefore, feature similarity between the crowd density map in the training data and an actual picture is effectively increased so that a regular pattern between the training data and the actual picture can be more readily learned by a convolutional neural network and an accuracy of the crowd counting system is improved.

Method for generating training data on basis of deformable Gaussian kernel in population counting system

Provided is an automatic train tracking method, including: acquiring and displaying a real-time video image captured by a current image capture device (S); wherein a plurality of image capture devices are sequentially arranged beforehand in a traveling direction of a train on a traveling route; detecting, based on the real-time video image, whether the train currently enters a capture range of the current image capture device (S); taking, when it is detected that the train enters the capture range of the current image capture device, a next image capture device as the current image capture device (S), returning to the step of acquiring and displaying a real-time video image captured by the current image capture device (S), wherein the next image capture device is an image capture device adjacent to the current image capture device in the traveling direction. Further disclosed is an automatic train tracking system.

Automatic train tracking method and automatic train tracking system

Growing community of inventors

Beijing, China

Xiangbin Kong