Near-chip Dynamic Vision Filtering for Low-Bandwidth Pedestrian Detection

04/03/2020

∙

by Anthony Bisulco, et al.

∙

SAMSUNG

∙

This paper presents a novel end-to-end system for pedestrian detection using Dynamic Vision Sensors (DVSs). We target applications where multiple sensors transmit data to a local processing unit, which executes a detection algorithm. Our system is composed of (i) a near-chip event filter that compresses and denoises the event stream from the DVS, and (ii) a Binary Neural Network (BNN) detection module that runs on a low-computation edge computing device (in our case a STM32F4 microcontroller). We present the system architecture and provide an end-to-end implementation for pedestrian detection in an office environment. Our implementation reduces transmission size by up to 99.6 transmitting the raw event stream. The average packet size in our system is only 1397 bits, while 307.2 kb are required to send an uncompressed DVS time window. Our detector is able to perform a detection every 450 ms, with an overall testing F1 score of 83 system make it ideal for IoT applications.

READ FULL TEXT

Near-chip Dynamic Vision Filtering for Low-Bandwidth Pedestrian Detection

Speck: A Smart event-based Vision Sensor with a low latency 327K Neuron Convolutional Neuronal Network Processing Pipeline

Real-time HOG+SVM based object detection using SoC FPGA for a UHD video stream

Illumination and Temperature-Aware Multispectral Networks for Edge-Computing-Enabled Pedestrian Detection

Naturalizing Neuromorphic Vision Event Streams Using GANs

EarCough: Enabling Continuous Subject Cough Event Detection on Hearables

Hardware architecture for high throughput event visual data filtering with matrix of IIR filters algorithm

OmniDRL: Robust Pedestrian Detection using Deep Reinforcement Learning on Omnidirectional Cameras

Near-chip Dynamic Vision Filtering for Low-Bandwidth Pedestrian Detection

Related Research

Speck: A Smart event-based Vision Sensor with a low latency 327K Neuron Convolutional Neuronal Network Processing Pipeline

Real-time HOG+SVM based object detection using SoC FPGA for a UHD video stream

Illumination and Temperature-Aware Multispectral Networks for Edge-Computing-Enabled Pedestrian Detection

Naturalizing Neuromorphic Vision Event Streams Using GANs

EarCough: Enabling Continuous Subject Cough Event Detection on Hearables

Hardware architecture for high throughput event visual data filtering with matrix of IIR filters algorithm

OmniDRL: Robust Pedestrian Detection using Deep Reinforcement Learning on Omnidirectional Cameras