TPH-YOLOv5++: Boosting Object Detection on Drone-Captured Scenarios with Cross-Layer Asymmetric Transformer

Zhao, Qi; Liu, Binghao; Lyu, Shuchang; Wang, Chunlei; Zhang, Hong

doi:10.3390/rs15061687

Cited by 35 publications

(22 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…)) (10) where c h is the height difference between the center point of the ground truth box and the prediction box, σ is the distance between the center point of the ground truth box and the prediction box, and, in fact, arcsin ( c h σ ) is equal to the angle α, defined as shown in Equations ( 11)- (13). where (𝑏 , 𝑏 ) is the ground truth box center coordinates, and (𝑏 , 𝑏 ) is the predicted box center coordinates.…”

Section: Loss Functionmentioning

confidence: 99%

“…The two-stage detection algorithms are represented by R-CNN and Fast R-CNN, necessitating the generation of region proposals and feature extraction by CNN, followed by object classification and localization using classifiers [11,12]. Zhao et al [13] enhanced the capability of YOLOv5 to identify remotely sensed images by integrating an extra cross-layer asymmetric transformer (CA-Trans) prediction head. The addition captures the asymmetric information between the head and others effectively, thanks to the use of a sparse local attention (SLA) module.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic and Efficient Detection of Loess Landslides Based on Deep Learning

Ji,

Liang,

Xie

et al. 2024

Sustainability

View full text Add to dashboard Cite

Frequent landslide disasters on the Loess Plateau in northwestern China have had a serious impact on the lives and production of the people in the region due to the fragile ecological environment and severe soil erosion. The effective monitoring and management of landslide hazards is hindered by the wide range of landslide features and scales in remotely sensed imagery, coupled with the shortage of local information and technology. To address this issue, we constructed a loess landslide dataset of 11,010 images and established a landslide detection network model. Coordinate Attention (CA) is integrated into the backbone with the aid of the YOLO model to capture precise location information and remote spatial interaction data from landslide images. Furthermore, the neck includes the Convolutional Block Attention Module (CBAM), which prompts the model to prioritize focusing on legitimate landslide objectives while also filtering out background noise to extract valid feature information. To efficiently extract classification and location details from landslide images, we introduce the lightweight Decoupled Head. This enhances detection accuracy for landslide objectives without excessively increasing model parameters. Furthermore, the utilization of the SIoU loss function improves angle perception for landslide detection algorithms and reduces the deviation between the predicted box and the ground truth box. The improved model achieves landslide object detection at multiple scales with a mAP of 92.28%, an improvement of 4.01% compared to the unimproved model.

show abstract

Section: Loss Functionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Automatic and Efficient Detection of Loess Landslides Based on Deep Learning

Ji,

Liang,

Xie

et al. 2024

Sustainability

View full text Add to dashboard Cite

show abstract

“…The accuracy of two-stage algorithm performs well, but there are some shortcomings in the detection speed, and it is difficult to achieve real-time computing on the platform with weak computing power. In respect of one-stage algorithm, YOLO Series [13,[17][18][19][20][21][22] can realize the regression of candidate boxes and classification of categories. The use of the attention mechanism in deep learning has improved the detection results.…”

Section: Of 16mentioning

confidence: 99%

Multi-Scale YOLOv5-AFAM Based Infrared Dim Small Target Detection

Wang¹,

Zhao²,

Ma³

et al. 2023

Preprint

View full text Add to dashboard Cite

Infrared detection plays an important role in the military, aerospace, and other fields, which has the advantages of all-weather, high stealth, and strong anti-interference. However, infrared dim small target detection suffers from complex backgrounds, low signal-to-noise ratio, blurred targets with small area percentages, and other challenges. In this paper, we proposed a multiscale YOLOv5-AFAM algorithm to realize high-accuracy and real-time detection. Aiming at the problem of target intra-class feature difference and inter-class feature similarity, the Adaptive Fusion Attention Module - AFAM was proposed to generate feature maps that are calculated to weigh the features in the network and make the network focus on small targets. This paper proposed a multiscale fusion structure to solve the problem of small and variable detection scales in infrared vehicle targets. In addition, the downsampling layer is improved by combining Maxpool and convolutional downsampling to reduce the number of model parameters and retain the texture information. For multiple scenarios, we constructed an infrared dim and small vehicle target detection dataset, ISVD. The multiscale YOLOv5-AFAM was conducted on the ISVD dataset, compared to YOLOv7, mAP@0.5 achieves a small improvement while the parameters are only 17.98% of it. By contrast with the YOLOv5s model, mAP@0.5 was improved by 4.3% with a 6.6% reduction in the parameters. Experiments results demonstrate that the multiscale YOLOv5-AFAM has a higher detection accuracy and detection speed on infrared dim and small vehicles.

show abstract

“…Another common approach for improving the detection head is to add an additional head specifically designed for detecting small objects to the existing three detection heads in YOLOv5. Researchers such as Baidya R [ 33 ] and Zhao Q [ 34 ] have adopted this approach and have extensively demonstrated its effectiveness in improving the network’s ability to detect small objects through numerous experiments.…”

Section: Related Workmentioning

confidence: 99%

YOLOv5s-DSD: An Improved Aerial Image Detection Algorithm Based on YOLOv5s

Sun

Chen

Xiao

et al. 2023

Sensors

View full text Add to dashboard Cite

Due to the challenges of small detection targets, dense target distribution, and complex backgrounds in aerial images, existing object detection algorithms perform poorly in aerial image detection tasks. To address these issues, this paper proposes an improved algorithm called YOLOv5s-DSD based on YOLOv5s. Specifically, the SPDA-C3 structure is proposed and used to reduce information loss while focusing on useful features, effectively tackling the challenges of small detection targets and complex backgrounds. The novel decoupled head structure, Res-DHead, is introduced, along with an additional small object detection head, further improving the network’s performance in detecting small objects. The original NMS is replaced by Soft-NMS-CIOU to address the issue of neighboring box suppression caused by dense object distribution. Finally, extensive ablation experiments and comparative tests are conducted on the VisDrone2019 dataset, and the results demonstrate that YOLOv5s-DSD outperforms current state-of-the-art object detection models in aerial image detection tasks. The proposed improved algorithm achieves a significant improvement compared with the original algorithm, with an increase of 17.4% in mAP@0.5 and 16.4% in mAP@0.5:0.95, validating the superiority of the proposed improvements.

show abstract

TPH-YOLOv5++: Boosting Object Detection on Drone-Captured Scenarios with Cross-Layer Asymmetric Transformer

Cited by 35 publications

References 52 publications

Automatic and Efficient Detection of Loess Landslides Based on Deep Learning

Automatic and Efficient Detection of Loess Landslides Based on Deep Learning

Multi-Scale YOLOv5-AFAM Based Infrared Dim Small Target Detection

YOLOv5s-DSD: An Improved Aerial Image Detection Algorithm Based on YOLOv5s

Contact Info

Product

Resources

About