Identifying The Detection Of Human And Non Human Decisions

2736 Words11 Pages
1 Abstract—Present work targets the detection of humans in images and videos. Our focus is on developing robust feature extraction algorithms that encode image regions as high dimensional feature vectors that support high accuracy human/non-human decisions. To test our feature sets we adopt a relatively simple learning framework that uses linear Support Vector Machines to classify each possible image region as a Human or as a non-Human. This work makes three main contributions. Firstly, we introduce grids of locally normalized Histograms of Oriented Gradients (HOG) as descriptors for people detection in static images. The HOG descriptors are computed over dense and overlapping grids of spatial blocks, with image gradient orientation features extracted at fixed resolution and gathered into a high dimensional feature vector. They are designed to be robust to small changes in image contour locations and directions, and significant changes in image illumination and color. Secondly, the Human detection algorithm has to be executed on modern parallel platforms to achieve the detection goal in real time. Thirdly, alert video monitoring station with an indication. It enhance the Real Time Streaming Protocol (RTSP) based Surveillance cameras purpose. Keywords—HOG, Feature extraction, Human detection, SVM classifier, GPU, RTSP. I. INTRODUCTION With the increasing danger of crime, video surveillance attracts much more attention and it has been adopted in different
Open Document