Small Object Detection Based on Microscale Perception and Enhancement-Location Feature Pyramid
- 7 May 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive and Developmental Systems
- Vol. 16 (6) , 1982-1996
Abstract
Due to the large number of small objects, significant scale variation, and uneven distribution in images captured by unmanned aerial vehicles (UAVs), existing algorithms have high rates of missing and false detections of small objects in drone images. A new object detection algorithm based on microscale perception and enhancement-location feature pyramid is proposed in this paper. The microscale perception module alternatives the original convolution module in backbone, changing the receptive field through two dilation branches with various dilation rates and an adjustment switch branch. To better match the size and shape of sampled targets, the weighted deformable convolution is employed. The enhancement-location feature pyramid module aggregates the features from each layer to obtain balanced semantic information and refines aggregated features to enhance their ability to represent features. Moreover, a bottom-up branch structure is added to utilize the property of lower-layer features being beneficial to locating small objects to enhance the localization ability for small objects. Additionally, by using specific image cropping and combining techniques, the target distribution of the training data is altered to make the model more sensitive to small objects and improving its robustness. Finally, a sample balance strategy is used in combination with Focal loss and a sample extraction control method to balance simple hard sample imbalance and the long-tail distribution of inter-class sample imbalance during training. Experimental results show that the proposed algorithm achieves a mean average precision of 35.9% on the VisDrone2019 dataset, which is a 14.2% improvement over the baseline Cascade RCNN and demonstrates better performance in detecting small objects in drone images. Compared with advanced algorithms in recent years, it also achieves state-of-the-art detection accuracy.Keywords
Funding Information
- Natural Science Foundation of China NSFC (61871445, 61302156)
- Key R&D Foundation Project of Jiangsu Province (BE2016001-4)
This publication has 56 references indexed in Scilit:
- EAS-SNN: End-to-End Adaptive Sampling and Representation for Event-Based Detection with Recurrent Spiking Neural Networks2024
- RFLA: Gaussian Receptive Field Based Label Assignment for Tiny Object Detection2022
- TTPLA: An Aerial-Image Dataset for Detection and Segmentation of Transmission Towers and Power Lines2021
- End-to-End Object Detection with Transformers2020
- Object Detection Using Clustering Algorithm Adaptive Searching Regions in Aerial Images2020
- Acquisition of Localization Confidence for Accurate Object Detection2018
- The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking2018
- SOD-MTGAN: Small Object Detection via Multi-Task Generative Adversarial Network2018
- PyramidBox: A Context-Assisted Single Shot Face Detector2018
- SSD: Single Shot MultiBox Detector2016