Developing a Compressed Object Detection Model based on YOLOv4 for Deployment on Embedded GPU Platform of Autonomous System

08/01/2021
by   Issac Sim, et al.
0

Latest CNN-based object detection models are quite accurate but require a high-performance GPU to run in real-time. They still are heavy in terms of memory size and speed for an embedded system with limited memory space. Since the object detection for autonomous system is run on an embedded processor, it is preferable to compress the detection network as light as possible while preserving the detection accuracy. There are several popular lightweight detection models but their accuracy is too low for safe driving applications. Therefore, this paper proposes a new object detection model, referred as YOffleNet, which is compressed at a high ratio while minimizing the accuracy loss for real-time and safe driving application on an autonomous system. The backbone network architecture is based on YOLOv4, but we could compress the network greatly by replacing the high-calculation-load CSP DenseNet with the lighter modules of ShuffleNet. Experiments with KITTI dataset showed that the proposed YOffleNet is compressed by 4.7 times than the YOLOv4-s that could achieve as fast as 46 FPS on an embedded GPU system(NVIDIA Jetson AGX Xavier). Compared to the high compression ratio, the accuracy is reduced slightly to 85.8 showed a high potential to be deployed on the embedded system of the autonomous system for the real-time and accurate object detection applications.

READ FULL TEXT

page 4

page 6

research
11/16/2020

FRDet: Balanced and Lightweight Object Detector based on Fire-Residual Modules for Embedded Processor of Autonomous Driving

For deployment on an embedded processor for autonomous driving, the obje...
research
09/18/2017

Fast YOLO: A Fast You Only Look Once System for Real-time Embedded Object Detection in Video

Object detection is considered one of the most challenging problems in t...
research
04/09/2019

Gaussian YOLOv3: An Accurate and Fast Object Detector Using Localization Uncertainty for Autonomous Driving

The use of object detection algorithms is becoming increasingly importan...
research
10/10/2022

Edge Device Deployment of Multi-Tasking Network for Self-Driving Operations

A safe and robust autonomous driving system relies on accurate perceptio...
research
04/03/2019

Super accurate low latency object detection on a surveillance UAV

Drones have proven to be useful in many industry segments such as securi...
research
02/10/2021

Robustness in Compressed Neural Networks for Object Detection

Model compression techniques allow to significantly reduce the computati...
research
05/21/2021

Analysis of voxel-based 3D object detection methods efficiency for real-time embedded systems

Real-time detection of objects in the 3D scene is one of the tasks an au...

Please sign up or login with your details

Forgot password? Click here to reset