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

By Mohammad Javad Shafiee, Brendan Chywl, Francis Li, Alexander Wong. arXiv.org, 2017

393 citations recorded by the source corpus.

Object detection is considered one of the most challenging problems in this field of computer vision, as it involves the combination of object classification and object localization within a scene. Recently, deep neural networks (DNNs) have been demonstrated to achieve superior object detection performance compared to other approaches, with YOLOv2 (an improved You Only Look Once model) being one of the state-of-the-art in DNN-based object detection methods in terms of both speed and accuracy. Although YOLOv2 can achieve real-time performance on a powerful GPU, it still remains very challenging for leveraging this approach for real-time object detection in video on embedded computing devices with limited computational power and limited memory. In this paper, we propose a new framework called Fast YOLO, a fast You Only Look Once framework which accelerates YOLOv2 to be able to perform object detection in video on embedded devices in a real-time manner. First, we leverage the evolutionary deep intelligence framework to evolve the YOLOv2 network architecture and produce an optimized architecture (referred to as O-YOLOv2 here) that has 2.8X fewer parameters with just a ~2% IOU drop. To further reduce power consumption on embedded devices while maintaining performance, a motion-adaptive inference method is introduced into the proposed Fast YOLO framework to reduce the frequency of deep inference with O-YOLOv2 based on temporal motion characteristics. Experimental results show that the proposed Fast YOLO framework can reduce the number of deep inferences by an average of 38.13%, and an average speedup of ~3.3X for objection detection in video compared to the original YOLOv2, leading Fast YOLO to run an average of ~18FPS on a Nvidia Jetson TX1 embedded system.

Subfields: Computer Vision and Pattern Recognition, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/7ba50b1edfb7f9497c8d663ed4adea4227a33c8a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Electrical and Electronic Engineering

Citations in the corpus

Object Detection Algorithm Based on Improved YOLOv3 (2020, methodology): “have proposed the Fast YOLO method, whereby YOLOv2 can be applied to embedded devices [16]: this employs an evolutionary deep intelligence framework to generate an optimized network architecture.”
AutoFocus: Efficient Multi-Scale Inference (2018, background): “Recently, a few methods have been proposed to accelerate multi-scale inference, but they have only been evaluated under constrained settings like pedestrian/face detection or object detection in videos [21, 56, 12, 53, 37, 27].”
Heterogeneity-Aware Cluster Scheduling Policies for Deep Learning Workloads (2020, background): “These accelerators have been deployed to great effect [25, 35] to train state-of-the-art deep neural network (DNN) models for many domains, including language, image and video [14, 30, 31, 51, 55].”