Implémentation en temps réel d'une architecture embarquée pour le comptage de passagers dans le transport public

Implémentation en temps réel d'une architecture embarquée pour le comptage de personnes dans une foule

International audience

A method based on texture feature and edge detection for people counting in a crowded area

We propose a population counting method for feature fusion and edge detection.The image is extracted from multiple information sources to estimate the count by image feature extraction and texture feature analysis, as well as for crowd head edge detection. We count people in high-density still images.For example, in the city bus station, subway. Our method uses a still image taken by the camera to estimate the count in the crowd density image, using multiple sources of information, namely: HOG, LBP, CANNY, these sources provides separate estimates of the number of counts and other statistical measures, through the support vector Machine SVM, classification, and regression analysis to obtain…

Multi-feature Counting of Dense Crowd Image Based on Multi-column Convolutional Neural Network

The crowd counting task is an important research problem. Now more and more people are concerned about safety issues. When the population density reaches a very high peak, the population density counts, the alarm is sent out, and the crowds are diverted. The trampling of the Shanghai New Year’s stampede will not happen again. The final density map is produced by two steps: at first, extract feature maps from multiple layers, and then adjust their output so that they are all the same size, all these resized layers are combined into the final density map. We also used texture features and target edge detection to reduce the loss of density map detail to better integrate with our convolutional…

Real-time implementation of counting people in a crowd on the embedded reconfigurable architecture on the unmanned aerial vehicle

The crowd counting task is an important research problem. Now more and more people are concerned about safety issues. Considering the scenario of a crowded scene: a population density system analyzes the crowds and triggers a warning to divert the crowds when their population density exceeds a normal range. With such a system, the incident of the Shanghai New Year's stampede will not happen again. The most difficult problem of population counting at present: On the one hand, in the densely populated area, how to make the model distinguish human head features more finely, such as head overlap. The second aspect is to find a small-scale local head feature in an image with a wide range of popu…

MFNet: Multi-feature convolutional neural network for high-density crowd counting

The crowd counting task involves the issue of security, so now more and more people are concerned about it. At present, the most difficult problem of population counting consists in: how to make the model distinguish human head features more finely in the densely populated area, such as head overlap and how to find a small-scale local head feature in an image with a wide range of population density. Facing these challenges, we propose a network for multiple feature convolutional neural network, which is called MFNet. It aims to get high-quality density maps in the high-density crowd scene, and at the same time to perform the task of the count and estimation of the crowd. In terms of crowd c…