Deep SCNN-based Real-time Object Detection for Self-driving Vehicles Using LiDAR Temporal Data

TL;DR

This paper introduces a spiking convolutional neural network integrated with YOLOv2 for real-time 3D object detection in self-driving vehicles, achieving comparable accuracy to CNNs but with significantly lower energy consumption.

Contribution

It develops a novel energy-efficient SCNN architecture with a data preprocessing layer and analog neuron circuit, enabling large-scale 3D object detection with reduced energy use.

Findings

Achieves competitive detection accuracy on KITTI dataset

Reduces energy consumption to 0.247mJ per inference

Maintains real-time performance at 35.7 fps

Abstract

Real-time accurate detection of three-dimensional (3D) objects is a fundamental necessity for self-driving vehicles. Most existing computer vision approaches are based on convolutional neural networks (CNNs). Although the CNN-based approaches can achieve high detection accuracy, their high energy consumption is a severe drawback. To resolve this problem, novel energy efficient approaches should be explored. Spiking neural network (SNN) is a promising candidate because it has orders-of-magnitude lower energy consumption than CNN. Unfortunately, the studying of SNN has been limited in small networks only. The application of SNN for large 3D object detection networks has remain largely open. In this paper, we integrate spiking convolutional neural network (SCNN) with temporal coding into the YOLOv2 architecture for real-time object detection. To take the advantage of spiking signals, we develop a novel data preprocessing layer that translates 3D point-cloud data into spike time data. We propose an analog circuit to implement the non-leaky integrate and fire neuron used in our SCNN, from which the energy consumption of each spike is estimated. Moreover, we present a method to calculate the network sparsity and the energy consumption of the overall network. Extensive experiments have been conducted based on the KITTI dataset, which show that the proposed network can reach competitive detection accuracy as existing approaches, yet with much lower average energy consumption. If implemented in dedicated hardware, our network could have a mean sparsity of 56.24% and extremely low total energy consumption of 0.247mJ only. Implemented in NVIDIA GTX 1080i GPU, we can achieve 35.7 fps frame rate, high enough for real-time object detection.