Log In Sign Up

SlimYOLOv3: Narrower, Faster and Better for Real-Time UAV Applications

by   Pengyi Zhang, et al.

Drones or general Unmanned Aerial Vehicles (UAVs), endowed with computer vision function by on-board cameras and embedded systems, have become popular in a wide range of applications. However, real-time scene parsing through object detection running on a UAV platform is very challenging, due to limited memory and computing power of embedded devices. To deal with these challenges, in this paper we propose to learn efficient deep object detectors through channel pruning of convolutional layers. To this end, we enforce channel-level sparsity of convolutional layers by imposing L1 regularization on channel scaling factors and prune less informative feature channels to obtain "slim" object detectors. Based on such approach, we present SlimYOLOv3 with fewer trainable parameters and floating point operations (FLOPs) in comparison of original YOLOv3 (Joseph Redmon et al., 2018) as a promising solution for real-time object detection on UAVs. We evaluate SlimYOLOv3 on VisDrone2018-Det benchmark dataset; compelling results are achieved by SlimYOLOv3 in comparison of unpruned counterpart, including 90.8 parameter size, running 2 times faster and comparable detection accuracy as YOLOv3. Experimental results with different pruning ratios consistently verify that proposed SlimYOLOv3 with narrower structure are more efficient, faster and better than YOLOv3, and thus are more suitable for real-time object detection on UAVs. Our codes are made publicly available at


page 7

page 8

page 9


Efficient Object Detection Model for Real-Time UAV Applications

Unmanned Aerial Vehicles (UAVs) especially drones, equipped with vision ...

Efficient resource management in UAVs for Visual Assistance

There is an increased interest in the use of Unmanned Aerial Vehicles (U...

ShuffleDet: Real-Time Vehicle Detection Network in On-board Embedded UAV Imagery

On-board real-time vehicle detection is of great significance for UAVs a...

Fast and Accurate, Convolutional Neural Network Based Approach for Object Detection from UAV

The ever-growing interest witnessed in the acquisition and development o...

Fast and Accurate Convolutional Object Detectors for Real-time Embedded Platforms

With the improvements in the object detection networks, several variatio...

Perceiving Traffic from Aerial Images

Drones or UAVs, equipped with different sensors, have been deployed in m...

Slim-neck by GSConv: A better design paradigm of detector architectures for autonomous vehicles

Object detection is a difficult downstream task in computer vision. For ...

Code Repositories


This page is for the SlimYOLOv3: Narrower, Faster and Better for UAV Real-Time Applications

view repo


Repository contains RetinaNet,Yolov3 and Faster RCNN for multi object detection on SIMD Dataset

view repo