Improving YOLOv7-Tiny for Infrared and Visible Light Image Object Detection on Drones

Hu, Shuming; Zhao, Fei; Lü, Huanzhang; Deng, Yingjie; Du, Jinming; Shen, Xinglin

doi:10.3390/rs15133214

Cited by 10 publications

(4 citation statements)

References 38 publications

(63 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared to methods dependent on centerline extraction models [18], our proposed reference point positioning technique identifies the location of inter-row navigation lines more accurately. Experimental results indicate that, among other YOLOv7 network model variants [28], our model exhibits the best balance between recognition accuracy and real-time processing capabilities. However, potential false positives and false negatives in the target detection algorithm may still lead to inaccuracies in reference point positioning.…”

Section: Discussionmentioning

confidence: 97%

“…However, the complexity of the network architecture and the large number of parameters in YOLOv7 network model make it demanding on device performance, rendering it unsuitable for edge terminal devices [26,27]. To address this issue, the researchers designed the YOLOv7-tiny network model based on YOLOv7 network model [28][29][30], which features a simplified structure specifically tailored for edge GPU devices [31]. YOLOv7-tiny network model consists of three components: the backbone network, the neck network, and the prediction head, as illustrated in Fig.…”

Section: Yolov7-tiny Network Modelmentioning

confidence: 99%

See 1 more Smart Citation

An Improved Method for Extracting Inter-Row Navigation Lines in Nighttime Maize Crops Using YOLOv7-Tiny

Gong,

Zhuang

2024

IEEE Access

View full text Add to dashboard Cite

In response to the issue of insufficient nighttime illumination in mechanical weeding of maize crops, this study proposes an improved YOLOv7-tiny network model infrared image object detection. The model incorporates the ShuffleNet v1 network to reduce computational complexity, enhance image feature extraction, and obtain more comprehensive semantic information. Additionally, the Coordinate Attention(CA) mechanism module is integrated into the neck network to improve sample detection performance. The EIOU loss function is employed to replace the original loss function, which results in faster model convergence and improved positioning accuracy. The improved YOLOv7-tiny network model is used to detect maize seedlings, with the center point of the detection box serving as the navigation reference point. Subsequently, the least squares method is used to fit the maize rows on both sides, thereby obtaining the inter-row navigation line in the middle of the two rows. Experimental results demonstrate that the improved YOLOv7-tiny network model achieves a detection accuracy of 94.21 % and a detection speed of 32.4 frames per second. Compared to the original YOLOv7 network model, it improves accuracy by 0.49 percentage points and frame rate by 4.6 frames per second, enabling accurate identification of maize seedlings at night. The average error between the extracted positioning reference points and the manually labeled midpoint of the corn seedlings is 4.85 cm, meeting navigation requirements of maize crop rows and providing feasibility for deployment on mobile terminal devices.

show abstract

Section: Discussionmentioning

confidence: 97%

Section: Yolov7-tiny Network Modelmentioning

confidence: 99%

An Improved Method for Extracting Inter-Row Navigation Lines in Nighttime Maize Crops Using YOLOv7-Tiny

Gong,

Zhuang

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…To address the problem of spatial information loss of small objects, the Spatial Information Enhancement Module (SIEM) is designed to adaptively learn the weak spatial information to be protected for small objects. In [23], anchor boxes are assigned according to the aspect ratio of the ground truth box to provide the network with prior information about the shape of the object. The network uses the Hard Sample Mining Loss (HSM Loss) function to guide learning and provide prior information about the shape of the object.…”

Section: Small Object Detectionmentioning

confidence: 99%

Unmanned Aerial Vehicle Perspective Small Target Recognition Algorithm Based on Improved YOLOv5

Zheng

Liu

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Small target detection has been widely used in applications that are relevant to everyday life and have many real-time requirements, such as road patrols and security surveillance. Although object detection methods based on deep learning have achieved great success in recent years, they are not effective in small target detection. In order to solve the problem of low recognition rate caused by factors such as low resolution of UAV viewpoint images and little valid information, this paper proposes an improved algorithm based on the YOLOv5s model, called YOLOv5s-pp. First, to better suppress interference from complex backgrounds and negative samples in images, we add a CA attention module, which can better focus on task-specific important channels while weakening the influence of irrelevant channels. Secondly, we improve the forward propagation and generalisation of the network using the Meta-ACON activation function, which adaptively learns to adjust the degree of linearity or nonlinearity of the activation function based on the input data. Again, the SPD Conv module is incorporated into the network model to address the problems of reduced learning efficiency and loss of fine-grained information due to cross-layer convolution in the model. Finally, the detection head is improved by using smaller, smaller-target detection heads to reduce missed detections. We evaluated the algorithm on the VisDrone2019-DET and UAVDT datasets and compared it with other state-of-the-art algorithms. Compared to YOLOv5s, mAP@.5 improved by 7.4% and 6.5% on the VisDrone2019-DET and UAVDT datasets, respectively, and compared to YOLOv8s, mAP@.5 improved by 0.8% and 2.1%, respectively. For improving the performance of the UAV-side small target detection algorithm, it will help to enhance the reliability and safety of UAVs in critical missions such as military reconnaissance, road patrol and security surveillance.

show abstract

“…While newer versions of YOLO may offer additional advancements, our research concentrated on YOLOv4 to establish a solid foundation for automatic bird detection. Future work could certainly explore the benefits of newer versions, such as YOLOv7 [34] and YOLOv7-tiny [35], considering their specific improvements, but our current focus was to demonstrate the effectiveness of YOLOv4 and YOLOv4-tiny in the context of bird-detection tasks.…”

Section: Future Workmentioning

confidence: 99%

Automated Wildlife Bird Detection from Drone Footage Using Computer Vision Techniques

et al. 2023

View full text Add to dashboard Cite

Wildlife conservationists have traditionally relied on manual identification and tracking of bird species to monitor populations and identify potential threats. However, many of these techniques may prove to be time-consuming. With the advancement of computer vision techniques, automated bird detection and recognition have become possible. In this manuscript, we present an application of an object-detection model for identifying and tracking wild bird species in natural environments. We used a dataset of bird images captured in the wild and trained the YOLOv4 model to detect bird species with high accuracy. We evaluated the model’s performance on a separate set of test images and achieved an average precision of 91.28%. Our method surpassed the time-consuming nature of manual identification and tracking, allowing for efficient and precise monitoring of bird populations. Through extensive evaluation on a separate set of test images, we demonstrated the performance of our model. Furthermore, our results demonstrated the potential of using YOLOv4 for automated bird detection and monitoring in the wild, which could help conservationists better understand bird populations and identify potential threats.

show abstract

Improving YOLOv7-Tiny for Infrared and Visible Light Image Object Detection on Drones

Cited by 10 publications

References 38 publications

An Improved Method for Extracting Inter-Row Navigation Lines in Nighttime Maize Crops Using YOLOv7-Tiny

An Improved Method for Extracting Inter-Row Navigation Lines in Nighttime Maize Crops Using YOLOv7-Tiny

Unmanned Aerial Vehicle Perspective Small Target Recognition Algorithm Based on Improved YOLOv5

Automated Wildlife Bird Detection from Drone Footage Using Computer Vision Techniques

Contact Info

Product

Resources

About