HOG Feature Extractor Hardware Accelerator for Real-Time Pedestrian Detection

Histogram of oriented gradients (HOG) is considered as the most promising algorithm in human detection, however its complexity and intensive computational load is an issue for real-time detection in embedded systems. This paper presents a hardware accelerator for HOG feature extractor to fulfill the requirements of real-time pedestrian detection in driver assistance systems. Parallel and deep pipelined hardware architecture with special defined memory access pattern is employed to improve the throughput while maintaining the accuracy of the original algorithm reasonably high. Adoption of efficient memory access pattern, which provides simultaneous access to the required memory area for different functional blocks, avoids repetitive calculation at different stages of computation, resulting in both higher throughput and lower power. It does not impose any further resource requirements with regard to memory utilization. Our presented hardware accelerator is capable of extracting HOG features for 60 fps (frame per second) of HDTV (1080x1920) frame and could be employed with several instances of support vector machine (SVM) classifier in order to provide multiple object detection.

[1]  Hiroyuki Ochi,et al.  Hardware Architecture for HOG Feature Extraction , 2009, 2009 Fifth International Conference on Intelligent Information Hiding and Multimedia Signal Processing.

[2]  Xuelong Li,et al.  Efficient HOG human detection , 2011, Signal Process..

[3]  Shintaro Izumi,et al.  Architectural Study of HOG Feature Extraction Processor for Real-Time Object Detection , 2012, 2012 IEEE Workshop on Signal Processing Systems.

[4]  Pei-Yin Chen,et al.  An Efficient Hardware Implementation of HOG Feature Extraction for Human Detection , 2014, IEEE Transactions on Intelligent Transportation Systems.

[5]  Silvio Savarese,et al.  EFFEX: An embedded processor for computer vision based feature extraction , 2011, 2011 48th ACM/EDAC/IEEE Design Automation Conference (DAC).

[6]  Yuichiro Shibata,et al.  Deep pipelined one-chip FPGA implementation of a real-time image-based human detection algorithm , 2011, 2011 International Conference on Field-Programmable Technology.

[7]  Calum G. Blair,et al.  Characterizing a Heterogeneous System for Person Detection in Video Using Histograms of Oriented Gradients: Power Versus Speed Versus Accuracy , 2013, IEEE Journal on Emerging and Selected Topics in Circuits and Systems.

[8]  Xing Li,et al.  A HOG Feature and SVM Based Method for Forward Vehicle Detection with Single Camera , 2013, 2013 5th International Conference on Intelligent Human-Machine Systems and Cybernetics.

[9]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[10]  Marek Gorgon,et al.  Floating point HOG implementation for real-time multiple object detection , 2012, 22nd International Conference on Field Programmable Logic and Applications (FPL).

[11]  Navneet Dalal,et al.  Finding People in Images and Videos , 2006 .

[12]  Seung-Eun Lee,et al.  Accelerating Histograms of Oriented Gradients descriptor extraction for pedestrian recognition , 2013, Comput. Electr. Eng..

[13]  Zhou Yuren,et al.  About Newton method , 2000 .

[14]  Ulrich Brunsmann,et al.  FPGA-Based Real-Time Pedestrian Detection on High-Resolution Images , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

[15]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[16]  Seonyoung Lee,et al.  HOG feature extractor circuit for real-time human and vehicle detection , 2012, TENCON 2012 IEEE Region 10 Conference.

[17]  Shintaro Izumi,et al.  A sub-100-milliwatt dual-core HOG accelerator VLSI for real-time multiple object detection , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.