Robust Object Detection in Aerial Imagery Based on Multi-Scale Detector and Soft Densely Connected

Object detection in aerial images is vital for autonomous guidance, navigation and control, and situational awareness. However, there are still many challenges facing researchers in this filed, including the target scales, the perspectives in taking pictures, and the highly complex background. The present paper introduces a robust object detector which is optimized for handling with multi-scale objects and the overhead capturing perspective object instances in aerial images. Firstly, in the feature extraction stage, an effective multi-scale detector (MSD) is designed to search for objects with different scales in feature maps. After that, when detecting a small target from a cluttered background, both the shallow and deep layer features are densely connected by the deconvolution after tackling the issues of low dimensionality in deep layers and inadequate representation of small objects. In the experiments part, we analyze the impacts of the above mentioned components on the model and make a comparison between the method at issue and other state-of-the-art approaches on two publicly-available datasets captured by satellites and high-altitude UAVs. The results show that the proposed method, which is applicable to a wider range of aerial images, is more effective and robust.

[1]  Kaiming He,et al.  Feature Pyramid Networks for Object Detection , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Qinghua Hu,et al.  Vision Meets Drones: A Challenge , 2018, ArXiv.

[3]  Kil To Chong,et al.  Object Detection in Very High-Resolution Aerial Images Using One-Stage Densely Connected Feature Pyramid Network , 2018, Sensors.

[4]  Jing Li,et al.  Real-Time Ground Vehicle Detection in Aerial Infrared Imagery Based on Convolutional Neural Network , 2018 .

[5]  Sang-Yeon Kim,et al.  Application of Deep-Learning Methods to Bird Detection Using Unmanned Aerial Vehicle Imagery , 2019, Sensors.

[6]  Lin Lei,et al.  Vehicle Detection in Aerial Images Based on Region Convolutional Neural Networks and Hard Negative Example Mining , 2017, Sensors.

[7]  Jianpei Zhang,et al.  A robust two-stage algorithm for local community detection , 2018, Knowl. Based Syst..

[8]  Baojiang Zhong,et al.  Building Corner Detection in Aerial Images with Fully Convolutional Networks , 2019, Sensors.

[9]  Frédéric Jurie,et al.  Vehicle detection in aerial imagery : A small target detection benchmark , 2016, J. Vis. Commun. Image Represent..

[10]  Liang Lin,et al.  Is Faster R-CNN Doing Well for Pedestrian Detection? , 2016, ECCV.

[11]  Congcong Li,et al.  Visual Detail Augmented Mapping for Small Aerial Target Detection , 2019, Remote. Sens..

[12]  Qixiang Ye,et al.  Orientation robust object detection in aerial images using deep convolutional neural network , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

[13]  Shuai Li,et al.  Rapid Airplane Detection in Remote Sensing Images Based on Multilayer Feature Fusion in Fully Convolutional Neural Networks , 2018, Sensors.

[14]  Naif Alajlan,et al.  Deep Attention Neural Network for Multi-Label Classification in Unmanned Aerial Vehicle Imagery , 2019, IEEE Access.

[15]  Ross B. Girshick,et al.  Focal Loss for Dense Object Detection , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Roberto Opromolla,et al.  A Vision-Based Approach to UAV Detection and Tracking in Cooperative Applications , 2018, Sensors.

[17]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Tong Liu,et al.  Extended faster R-CNN for long distance human detection: Finding pedestrians in UAV images , 2018, 2018 IEEE International Conference on Consumer Electronics (ICCE).

[19]  S. A. Lyasheva,et al.  Image analysis in unmanned aerial vehicle on-board system for objects detection and recognition with the help of energy characteristics based on wavelet transform , 2017, Optical Technologies for Telecommunications.

[20]  Bernt Schiele,et al.  What Makes for Effective Detection Proposals? , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  King Ngi Ngan,et al.  Simultaneously Detecting and Counting Dense Vehicles From Drone Images , 2019, IEEE Transactions on Industrial Electronics.

[22]  Junwei Han,et al.  A Survey on Object Detection in Optical Remote Sensing Images , 2016, ArXiv.

[23]  Chee Peng Lim,et al.  Robust Vehicle Detection in Aerial Images Using Bag-of-Words and Orientation Aware Scanning , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[24]  Jinghua Zhang,et al.  Design and Training of Deep CNN-Based Fast Detector in Infrared SUAV Surveillance System , 2019, IEEE Access.

[25]  Ali Farhadi,et al.  YOLOv3: An Incremental Improvement , 2018, ArXiv.

[26]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[27]  Ming Zhu,et al.  Vehicle Detection in Aerial Images Using a Fast Oriented Region Search and the Vector of Locally Aggregated Descriptors , 2019, Sensors.

[28]  Kai Zhao,et al.  Res2Net: A New Multi-Scale Backbone Architecture , 2019, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[29]  Jiebo Luo,et al.  DOTA: A Large-Scale Dataset for Object Detection in Aerial Images , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[30]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[31]  Mohamed S. Shehata,et al.  KRMARO: Aerial Detection of Small-Size Ground Moving Objects Using Kinematic Regularization and Matrix Rank Optimization , 2019, IEEE Transactions on Circuits and Systems for Video Technology.

[32]  Yang Long,et al.  Learning RoI Transformer for Oriented Object Detection in Aerial Images , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[33]  Lin Lei,et al.  Fast vehicle detection in UAV images , 2017, 2017 International Workshop on Remote Sensing with Intelligent Processing (RSIP).

[34]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[35]  Mohamed S. Shehata,et al.  An Accelerated Sequential PCP-Based Method for Ground-Moving Objects Detection From Aerial Videos , 2019, IEEE Transactions on Image Processing.

[36]  Qiong Liu,et al.  Scale adaptive image cropping for UAV object detection , 2019, Neurocomputing.

[37]  Lin Lei,et al.  Arbitrary-Oriented Vehicle Detection in Aerial Imagery with Single Convolutional Neural Networks , 2017, Remote. Sens..

[38]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[39]  Tao Lei,et al.  Robust Vehicle Detection in Aerial Images Based on Cascaded Convolutional Neural Networks , 2017, Sensors.

[40]  Jürgen Beyerer,et al.  Deep learning based multi-category object detection in aerial images , 2017, Defense + Security.

[41]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[42]  Saeid Nahavandi,et al.  Orientation aware vehicle detection in aerial images , 2017 .