Search

Small object detection is widely used in a variety of fields such as automatic driving, UAV-based object detection, and aerial image detection. However, small objects carry limited information, making it difficult for detectors to detect small objects. In recent years, the development of deep learning has significantly improved the performance of small object detection. This paper provides a comprehensive review to help further the development of small target detection. We summarize the challenges related to small object detection and analyze solutions to these challenges in existing works, including integrating the feature at different layers, enriching available information, balancing the number of positive and negative samples for small objects, and increasing sufficient small object instances. We discuss related methods developed in three application areas, including automatic driving, UAV search and rescue, and aerial image detection. In addition, we thoroughly analyze the performance of typical small object detection methods on popular datasets. Finally, based on the comprehensive review of small object detection methods, we point out possible research directions for future studies. [ABSTRACT FROM AUTHOR]

In the natural environment, the detection and recognition process of Punna navel orange fruit using machine vision systems is affected by many factors, such as complex background, uneven light illumination, occlusions of branches and leaves and large variations in fruit size. To solve these problems of low accuracy in fruit detection and poor robustness of the detection algorithm in the field conditions, a new object detection algorithm, named Retinanet_G2S, was proposed in this paper based on the modified Retinanet network. The images of Punna navel orange were collected with Microsoft Kinect V2 in the uncontrolled environment. Firstly, a new Res2Net-GF network was designed to replace the section of feature extraction in the original Retinanet, which can potentially improve the learning ability of target features of the trunk network. Secondly, a multi-scale cross-regional feature fusion grids network was designed to replace the feature pyramid network module in the original Retinanet, which could enhance the ability of feature information fusion among different scales of the feature pyramid. Finally, the original border regression localization method in Retinanet network was optimized based on the accurate boundary box regression algorithm. The study results showed that, compared with the original Retinanet network, Retinanet_G2S improved mAP, mAP50, mAP75, mAPS, mAPM and mAPL by 3.8%, 1.7%, 5.8%, 2.4%, 2.1% and 5.5%, respectively. Moreover, compared with 7 types of classic object detection models, including SSD, YOLOv3, CenterNet, CornerNet, FCOS, Faster-RCNN and Retinanet, the average increase in mAP of Retinanet_G2S was 9.11%. Overall, Retinanet_G2S showed a promising optimization effect, particularly for the detection of small targets and overlapping fruits. [ABSTRACT FROM AUTHOR]

Object detection from UAV (unmanned aerial vehicle) images is a crucial and challenging task in the field of computer vision. The task suffers from the difficulties of small dense objects, low pixel occupation of objects, and features that are not easily extracted in images. In this paper, we proposed a multilayer feature fusion algorithm named SCA-YOLO (spatial and coordinate attention enhancement YOLO) for small object detection with hybrid attention mechanisms. It uses the single-stage detection algorithm YOLOv5 as the base framework. Firstly, a hybrid attention module with associated coordinate attention is designed to enhance the feature extraction of small objects. Secondly, to address the problem that small objects are vulnerable to being disturbed by the complex background information on UAV images, an improved SEB (simple and efficient bottleneck) module is designed to further distinguish foreground and background features. Thirdly, a multilayer feature fusion structure is built to perform channel stitching of shallow and deep feature maps, as well as to enrich the semantic information of shallow features by adding horizontal jump connections. Finally, experiments are conducted on the VisDrone2020 dataset, which involves a large number of small objects photographed by drones. In addition, we also conduct extended experiments on the DOTA dataset and PASCAL VOC dataset. Comparative experimental results indicate that the proposed method considerably improves the accuracy of small object detection on multiple benchmark datasets. [ABSTRACT FROM AUTHOR]