Results 1 to 10 of about 832,071 (273)

Efficient Small Object Detection You Only Look Once: A Small Object Detection Algorithm for Aerial Images [PDF]

Sensors
Aerial images have distinct characteristics, such as varying target scales, complex backgrounds, severe occlusion, small targets, and dense distribution.
Jie Luo, Zhicheng Liu, Yibo Wang, Ao Tang, Huahong Zuo, Ping Han   +5 more
doaj   +4 more sources

Toward Versatile Small Object Detection with Temporal-YOLOv8 [PDF]

Sensors
Deep learning has become the preferred method for automated object detection, but the accurate detection of small objects remains a challenge due to the lack of distinctive appearance features.
Martin C. van Leeuwen, Ella P. Fokkinga, Wyke Huizinga, Jan Baan, Friso G. Heslinga   +4 more
doaj   +5 more sources

Small Object Detection with Multiscale Features [PDF]

International Journal of Digital Multimedia Broadcasting, 2018
The existing object detection algorithm based on the deep convolution neural network needs to carry out multilevel convolution and pooling operations to the entire image in order to extract a deep semantic features of the image.
Guo X. Hu, Zhong Yang, Lei Hu, Li Huang, Jia M. Han   +4 more
doaj   +2 more sources

Lightweight multi-scale network for small object detection [PDF]

PeerJ Computer Science, 2022
Small object detection is widely used in the real world. Detecting small objects in complex scenes is extremely difficult as they appear with low resolution.
Li Li, Bingxue Li, Hongjuan Zhou
doaj   +4 more sources

Improved Small Object Detection Algorithm CRL-YOLOv5

Sensors
Detecting small objects in images poses significant challenges due to their limited pixel representation and the difficulty in extracting sufficient features, often leading to missed or false detections.
Zhiyuan Wang, Shujun Men, Yuntian Bai, Yutong Yuan, Jiamin Wang, Kanglei Wang, Lei Zhang   +6 more
doaj   +3 more sources

Feature-Fused SSD: Fast Detection for Small Objects [PDF]

Ninth International Conference on Graphic and Image Processing (ICGIP 2017), 2018
Small objects detection is a challenging task in computer vision due to its limited resolution and information. In order to solve this problem, the majority of existing methods sacrifice speed for improvement in accuracy.
Bell, Chen, Fu, Girshick, Girshick, He, He, Hu, Jia, Liu, Redmon, Ren, Simonyan, Zeng   +13 more
core   +2 more sources

Improving Small Object Proposals for Company Logo Detection [PDF]

Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval, 2017
Many modern approaches for object detection are two-staged pipelines. The first stage identifies regions of interest which are then classified in the second stage.
Bell S., Eggert C., Ioffe S., Oliveira G., Redmon J., Simonyan K., Zitnick L.   +6 more
core   +4 more sources

PCPE-YOLO with a lightweight dynamically reconfigurable backbone for small object detection [PDF]

Scientific Reports
In the domain of object detection, small object detection remains a pressing challenge, as existing approaches often suffer from limited accuracy, high model complexity, and difficulty meeting lightweight deployment requirements.
Weijia Chen, Jiaming Liu, Tong Liu, Yaoming Zhuang   +3 more
doaj   +2 more sources

MDFE-Net: a multiscale dilated feature enhancement network for small object detection [PDF]

Frontiers in Plant Science
Due to the lack of feature information and complex background, the task of small object detection is very challenging. To solve these problems, this paper proposes two small object detection performance enhancement modules for multiple detection tasks ...
Tianzhe Liu, Shihang Lin, Jiayi Zhang, Bin Li, Junyan Zhu   +4 more
doaj   +2 more sources

SOD-YOLO: A lightweight small object detection framework

Scientific Reports
Currently, lightweight small object detection algorithms for unmanned aerial vehicles (UAVs) often employ group convolutions, resulting in high Memory Access Cost (MAC) and rendering them unsuitable for edge devices that rely on parallel computing.
Yunze Xiao, Nan Di
doaj   +3 more sources