Histogram of Oriented Gradients Feature Extraction From Raw Bayer Pattern Images

This brief studies the redundancy in the image processing pipeline for histogram of oriented gradients (HOG) feature extraction. The impact of demosaicing on the extracted HOG features is analyzed and experimented. It is shown that by taking advantage of the inter-channel correlation of natural images, the HOG features can be directly extracted from the Bayer pattern images with proper gamma compression. Due to the elimination of the image processing pipeline, the power consumption and computational complexity of the detection system can be significantly reduced. Experimental results show that the Bayer pattern image-based HOG features can be used in pedestrian detection systems with little performance degradation.

[1]  Ludovic Macaire,et al.  Edge detection from Bayer color filter array image , 2018 .

[2]  Yan-ping Chen,et al.  Fast hog feature computation based on CUDA , 2011, 2011 IEEE International Conference on Computer Science and Automation Engineering.

[3]  António J. R. Neves,et al.  Real-Time Color Coded Object Detection Using a Modular Computer Vision Library , 2016 .

[4]  António J. R. Neves,et al.  On the Use of Feature Descriptors on Raw Image Data , 2016, ICPRAM.

[5]  Sally L. Wood,et al.  Focal plane processing for HOG detection with Bayer pattern sensors , 2016, 2016 50th Asilomar Conference on Signals, Systems and Computers.

[6]  David A. McAllester,et al.  Object Detection with Discriminatively Trained Part Based Models , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Vivienne Sze,et al.  A 58.6 mW 30 Frames/s Real-Time Programmable Multiobject Detection Accelerator With Deformable Parts Models on Full HD $1920\times 1080$ Videos , 2017, IEEE Journal of Solid-State Circuits.

[8]  Kari Pulli,et al.  FlexISP , 2014, ACM Trans. Graph..

[9]  W. Marsden.  I and J , 2012 .

[10]  Hui Xiong,et al.  Fast Pedestrian Detection Based on HOG-PCA and Gentle AdaBoost , 2012, 2012 International Conference on Computer Science and Service System.

[11]  Ludovic Macaire,et al.  CFA local binary patterns for fast illuminant-invariant color texture classification , 2012, Journal of Real-Time Image Processing.

[12]  Pietro Perona,et al.  Integral Channel Features , 2009, BMVC.

[13]  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).

[14]  Suren Jayasuriya,et al.  Reconfiguring the Imaging Pipeline for Computer Vision , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[15]  Yuichiro Shibata,et al.  FPGA Implementation of Human Detection by HOG Features with AdaBoost , 2013, IEICE Trans. Inf. Syst..

[16]  Qing Jun Wang,et al.  LPP-HOG: A New Local Image Descriptor for Fast Human Detection , 2008, 2008 IEEE International Symposium on Knowledge Acquisition and Modeling Workshop.

[17]  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.

[18]  Andrew Zisserman,et al.  Representing shape with a spatial pyramid kernel , 2007, CIVR '07.

[19]  Boris Murmann,et al.  Toward Always-On Mobile Object Detection: Energy Versus Performance Tradeoffs for Embedded HOG Feature Extraction , 2018, IEEE Transactions on Circuits and Systems for Video Technology.

[20]  Yücel Altunbasak,et al.  Color plane interpolation using alternating projections , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.