A novel acceleration strategy is presented for computer vision and machine learning field from both algorithmic and hardware implementation perspective. With our approach, complex mathematical functions such as multiplication can be greatly simplified. As a result, an accelerated machine learning method requires no more than ADD operations, which tremendously reduces processing time, hardware complexity and power consumption. The applicability is illustrated by going through a machine learning example of HOG+SVM, where the accelerated version achieves comparable accuracy based on real datasets of human figure and digits.
For the analysis of the interaction patterns of traffic participants, a robust visual detector and tracker for pedestrians and vehicles has been developed. The resulting implementation is currently being used to analyze hundreds of hours of recorded videos. This work concentrates on the detector for pedestrians, which combines several key concepts into a processing framework, which can run close to real-time even without GPU acceleration: a fast and efficient HOG detector cascade is combined with a deep convolutional network to combine the advantages of both algorithms. In addition to the detector, this work covers also aspects of camera calibration, which is used to control the scale of detection windows based on the viewing geometry. The evaluation of our detector on the CALTECH database as well as on real world ground truth videos and manually annotated sample data demonstrates the effectiveness of our approach.
This paper proposes a real-time vehicle tracking and type recognition system. An object tracker is recruited to detect vehicles within CCTV video footage. Subsequently, the vehicle region-of-interest within each frame are analysed using a set of features that consists of Region Features, Histogram of Oriented Gradient (HOG) and Local Binary Pattern (LBP) histogram features. Finally, a Support Vector Machine (SVM) is recruited as the classification tool to categorize vehicles into two classes: cars and vans. The proposed technique was tested on a dataset of 60 vehicles comprising of a mix of frontal/rear and angular views. Experimental results prove that the proposed technique offers a very high level of accuracy thereby promising applicability in real-life situations.