A 35μW 64 × 64 Pixels Vision Sensor Embedding Local Binary Pattern Code Computation

This paper presents a 64 × 64 pixels vision sensor embedding pixel-wise computation of the Local Binary Pattern (LBP) code, which is an oriented, binary, vector contrast that is widely used for texture description and retrieval. For each pixel, the sensor estimates the LBP code over four neighbors in a 3×3 pixel kernel. The image processing is performed inside each pixel during the integration time over a dynamic range up to 98dB, thanks to a pixel-level auto-exposure control. The contrast detection relies on the estimation of the time difference between two pixels thresholded against two reference voltages. The four binary signed contrast vectors are delivered to the output, coded into 4-bit/pixel. The 0.35μm CMOS sensor features a power consumption of 35μW at 3.3V and 15fps.

[1]  Loris Nanni,et al.  Survey on LBP based texture descriptors for image classification , 2012, Expert Syst. Appl..

[2]  Matti Pietikäinen,et al.  Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Di Huang,et al.  Local Binary Patterns and Its Application to Facial Image Analysis: A Survey , 2011, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[4]  S. Malathi,et al.  An efficient method for partial fingerprint recognition based on local binary pattern , 2010, 2010 INTERNATIONAL CONFERENCE ON COMMUNICATION CONTROL AND COMPUTING TECHNOLOGIES.

[5]  Bernabé Linares-Barranco,et al.  A Spatial Contrast Retina With On-Chip Calibration for Neuromorphic Spike-Based AER Vision Systems , 2007, IEEE Transactions on Circuits and Systems I: Regular Papers.

[6]  Caifeng Shan,et al.  Learning local binary patterns for gender classification on real-world face images , 2012, Pattern Recognit. Lett..

[7]  Jaehyuk Choi,et al.  A 3.4µW CMOS image sensor with embedded feature-extraction algorithm for motion-triggered object-of-interest imaging , 2013, 2013 IEEE International Solid-State Circuits Conference Digest of Technical Papers.

[8]  Matti Pietikäinen,et al.  Local Binary Patterns for Still Images , 2011 .

[9]  Massimo Gottardi,et al.  A 30 µW 30 fps 110 × 110 Pixels Vision Sensor Embedding Local Binary Patterns , 2015, IEEE Journal of Solid-State Circuits.

[10]  Youdong Ding,et al.  Recognition of hand-gestures using improved local binary pattern , 2011, 2011 International Conference on Multimedia Technology.

[11]  Pierre-Yves Burgi,et al.  A 128 /spl times/ 128 pixel 120 dB dynamic range vision sensor chip for image contrast and orientation extraction , 2003, 2003 IEEE International Solid-State Circuits Conference, 2003. Digest of Technical Papers. ISSCC..

[12]  R. Etienne-Cummings,et al.  Temporal change threshold detection imager , 2005, ISSCC. 2005 IEEE International Digest of Technical Papers. Solid-State Circuits Conference, 2005..

[13]  Li Song,et al.  Dynamic background subtraction based on spatial extended center-symmetric local binary pattern , 2010, 2010 IEEE International Conference on Multimedia and Expo.

[14]  Michela Lecca,et al.  On the von Kries Model: Estimation, Dependence on Light and Device, and Applications , 2014 .