Histogram of Oriented Gradients Feature Extraction Without Normalization
Authors:
- Ling ZhangLZLing Zhang
- Wei ZhouWZWei Zhou
- Jingwei LiJLJingwei Li
- Juan LiJLJuan Li
- Xin LouXLXin Lou
- 8 December 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 252-255
Abstract
In this paper, the effects of normalization in the histogram of oriented gradients (HOG) are studied and a HOG feature extraction pipeline without normalization is proposed. In the proposed pipeline, the functionality of normalization is merged into the gradient generation step by replacing the original linear difference based gradients with logarithmic gradients. Due to the discrete property of the pixel values, the logarithmic operation can be easily implemented using a lookup table (LUT) with a depth of 2 N , where N is the bit-width of the pixels. Theoretical analysis and experimental results show that the proposed normalization-free HOG feature based logarithmic gradient is close to the original version and can be used in the pedestrian detection algorithms without performance degradation. It is shown in the experiments that by skipping the time-consuming normalization step, the processing speed of HOG feature extraction can be significantly improved.Keywords
This publication has 9 references indexed in Scilit:
- Towards Reaching Human Performance in Pedestrian DetectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- A 58.6mW real-time programmable object detector with multi-scale multi-object support using deformable parts model on 1920×1080 video at 30fps2016
- An Energy-Efficient Hardware Implementation of HOG-Based Object Detection at 1080HD 60 fps with Multi-Scale SupportJournal of Signal Processing Systems, 2015
- Passenger Compartment Violation Detection in HOV/HOT LanesIEEE Transactions on Intelligent Transportation Systems, 2015
- Pedestrian Detection: An Evaluation of the State of the ArtIEEE Transactions on Pattern Analysis and Machine Intelligence, 2011
- The Fastest Pedestrian Detector in the West2010
- Pedestrian detection: A benchmark2009
- Histograms of Oriented Gradients for Human Detection2005
- Vision for mobile robot navigation: a surveyIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002