Improved YOLOv5 for Aerial Images Based on Attention Mechanism

Zebin, Li; Fan, Bangkui; Xu, Yulong; Sun, Ruizhi

doi:10.1109/access.2023.3277931

Cited by 2 publications

(1 citation statement)

References 27 publications

(27 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhu et al 8 integrated the transformer 9 into the detection head of YOLOv5s to enhance the representation capability of object features. Li et al 10 inserted the Swin transformer 11 into the backbone network and neck end of YOLOv5s to capture the context of objects and reduce interference from background information. These methods effectively improved the model's precision in locating objects, particularly small ones.…”

Section: Introductionmentioning

confidence: 99%

LRSNet: a high-efficiency lightweight model for object detection in remote sensing

Zhu,

Miao,

Wang

2024

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

Unmanned aerial vehicles (UAVs) exhibit the ability to flexibly conduct aerial remotesensing imaging. By employing deep learning object-detection algorithms, they efficiently perceive objects, finding widespread application in various practical engineering tasks. Consequently, UAV-based remote sensing object detection technology holds considerable research value. However, the background of UAV remote sensing images is often complex, with varying shooting angles and heights leading to difficulties in unifying target scales and features. Moreover, there is the challenge of numerous densely distributed small targets. In addition, UAVs face significant limitations in terms of hardware resources. Against this background, we propose a lightweight remote sensing object detection network (LRSNet) model based on YOLOv5s. In the backbone of LRSNet, the lightweight network MobileNetV3 is used to substantially reduce the model's computational complexity and parameter count. In the model's neck, a multiscale feature pyramid network named CM-FPN is introduced to enhance the detection capability of small objects. CM-FPN comprises two key components: C3EGhost, based on GhostNet and efficient channel attention modules, and the multiscale feature fusion channel attention mechanism (MFFC). C3EGhost, serving as CM-FPN's primary feature extraction module, possesses lower computational complexity and fewer parameters, as well as effectively reducing background interference. MFFC, as the feature fusion node of CM-FPN, can adaptively weight the fusion of shallow and deep features, acquiring more effective details and semantic information for object detection. LRSNet, evaluated on the NWPU VHR-10, DOTA V1.0, and VisDrone-2019 datasets, achieved mean average precision of 94.0%, 71.9%, and 35.6%, with Giga floating-point operations per second and Param (M) measuring only 5.8 and 4.1, respectively. This outcome affirms the efficiency of LRSNet in UAV-based remote-sensing object detection tasks.

show abstract

Section: Introductionmentioning

confidence: 99%