CEAM-YOLOv7: Improved YOLOv7 Based on Channel Expansion and Attention Mechanism for Driver Distraction Behavior Detection

Liu, Shugang; Wang, Yujie; Yu, Qiangguo; Liu, Hongli; Peng, Z.-S.

doi:10.1109/access.2022.3228331

Cited by 57 publications

(31 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recall is the ratio of true positives (TP) to all ground truths. F1 score is calculated as the harmonic mean of the precision and recall values [ 33 ], which indicates better target detection accuracy [ 34 ]. The F1 score ranges between 0 and 1, with a higher value indicating better model performance, as detailed in these papers [ 35 , 36 , 37 , 38 , 39 , 40 ].…”

Section: Resultsmentioning

confidence: 99%

Fire Detection and Notification Method in Ship Areas Using Deep Learning and Computer Vision Approaches

Avazov

Jamil

Muminov

et al. 2023

Sensors

View full text Add to dashboard Cite

Fire incidents occurring onboard ships cause significant consequences that result in substantial effects. Fires on ships can have extensive and severe wide-ranging impacts on matters such as the safety of the crew, cargo, the environment, finances, reputation, etc. Therefore, timely detection of fires is essential for quick responses and powerful mitigation. The study in this research paper presents a fire detection technique based on YOLOv7 (You Only Look Once version 7), incorporating improved deep learning algorithms. The YOLOv7 architecture, with an improved E-ELAN (extended efficient layer aggregation network) as its backbone, serves as the basis of our fire detection system. Its enhanced feature fusion technique makes it superior to all its predecessors. To train the model, we collected 4622 images of various ship scenarios and performed data augmentation techniques such as rotation, horizontal and vertical flips, and scaling. Our model, through rigorous evaluation, showcases enhanced capabilities of fire recognition to improve maritime safety. The proposed strategy successfully achieves an accuracy of 93% in detecting fires to minimize catastrophic incidents. Objects having visual similarities to fire may lead to false prediction and detection by the model, but this can be controlled by expanding the dataset. However, our model can be utilized as a real-time fire detector in challenging environments and for small-object detection. Advancements in deep learning models hold the potential to enhance safety measures, and our proposed model in this paper exhibits this potential. Experimental results proved that the proposed method can be used successfully for the protection of ships and in monitoring fires in ship port areas. Finally, we compared the performance of our method with those of recently reported fire-detection approaches employing widely used performance matrices to test the fire classification results achieved.

show abstract

Section: Resultsmentioning

confidence: 99%

Fire Detection and Notification Method in Ship Areas Using Deep Learning and Computer Vision Approaches

Avazov

Jamil

Muminov

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…The principle of yolov7 is to segment the input image into feature maps, and then convert the feature maps into detection frame positions and category probabilities through a multi-layer convolutional neural network, and finally form the detection results. Yolov7 is faster and more accurate than the previous generation yolov5 [16][17][18] .…”

Section: Deep Neural Network：yolov7mentioning

confidence: 95%

Convolutional neural network-based crack identification and detection in underwater buildings

Sun

2024

Sixth Conference on Frontiers in Optical Imaging and Technology: Novel Technologies in Optical Systems

View full text Add to dashboard Cite

Underwater cracks are a common problem in buildings and infrastructure, and their presence can have a significant impact on the stability and safety of the structure. Therefore, early detection and repair of cracks is very important. However, traditional underwater crack detection methods usually require manual involvement, which is time-consuming and dangerous. Therefore, it is of great significance to develop an automated crack identification and detection system that can be mounted on an underwater robot. For traditional underwater crack detection, the obtained underwater video is usually segmented and preprocessed, and the obtained data is input into a computer vision-based system for crack recognition and detection, which is much less efficient than the current deep learning methods. In this paper, two kinds of underwater building crack recognition network and detection network based on convolutional neural network are proposed respectively, by collecting different light, depth, turbidity and other multi-waters video materials, after a series of computer vision processing, it will be input into the neural network for the expansion of the data set, and the obtained data set is divided into test set, training set and validation set, and the training set will be input into the neural network used for the target recognition to be trained, to get the comprehensive recognition model of cracks in underwater complex environment. The size and shape of the cracks are manually depicted using the training set, and inputted into the neural network for crack detection to obtain the complex background underwater crack detection model. Using the complex background underwater crack detection model to detect the underwater environment through the neural network for target recognition, the underwater robot equipped with a waterproof and anti-shaking camera communicates with the shore and moves, follows the recognition results of the neural network for target recognition to lock the crack location, and then manipulates the underwater robot to approach the target crack, and then uses the neural network for target recognition to detect the underwater crack with a complex background using the complex background underwater crack detection model. The neural network for target recognition uses a complex background underwater crack detection model to segment the scaled underwater video captured by the camera and process it in high-definition to map the length and width of the cracks with pixel-level accuracy, and then transmits the data to the shore in real time to complete the identification and detection of cracks in underwater buildings.

show abstract

“…It reprocesses the target detection problem into a regression problem for computational analysis, which can be realized from the direct input of the original image to the output of the target location and target category. It is a real end-to-end training scheme with fast analysis speed, high accuracy, and strong generalization ability, and has been widely used in the field of real-time target detection [37][38][39]. The computational principle of YOLO is to first input an image and divide the image into different grids according to certain rules, with each grid being responsible for predicting multiple bounding boxes while giving the confidence level of each window.…”

Section: Yolov7 Algorithmmentioning

confidence: 99%

SE-YOLOv7 Landslide Detection Algorithm Based on Attention Mechanism and Improved Loss Function

Liu,

Wu,

Deng

et al. 2023

Land

View full text Add to dashboard Cite

With the continuous development of computer vision technology, more and more landslide identification detection tasks have started to shift from manual visual interpretation to automatic computer identification, and automatic landslide detection methods based on remote sensing satellite images and deep learning have been gradually developed. However, most existing algorithms often have the problem of low precision and weak generalization in landslide detection. Based on the Google Earth Engine platform, this study selected landslide image data from 24 study areas in China and established the DN landslide sample dataset, which contains a total of 1440 landslide samples. The original YOLOv7 algorithm model was improved and optimized by applying the SE squeezed attention mechanism and VariFocal loss function to construct the SE-YOLOv7 model to realize the automatic detection of landslides in remote sensing images. The experimental results show that the mAP, Precision value, Recall value, and F1-Score of the improved SE-YOLOv7 model for landslide identification are 91.15%, 93.35%, 94.54%, and 93.94%, respectively. At the same time, through a field investigation and verification study in Qianyang County, Baoji City, Shaanxi Province, comparing the detection results of SE-YOLOv7, it is concluded that the improved SE-YOLOv7 can locate the landslide location more accurately, detect the landslide range more accurately, and have fewer missed detections. The research results show that the algorithm model has strong detection accuracy for many types of landslide image data, which provides a technical reference for future research on landslide detection based on remote sensing images.

show abstract

CEAM-YOLOv7: Improved YOLOv7 Based on Channel Expansion and Attention Mechanism for Driver Distraction Behavior Detection

Cited by 57 publications

References 27 publications

Fire Detection and Notification Method in Ship Areas Using Deep Learning and Computer Vision Approaches

Fire Detection and Notification Method in Ship Areas Using Deep Learning and Computer Vision Approaches

Convolutional neural network-based crack identification and detection in underwater buildings

SE-YOLOv7 Landslide Detection Algorithm Based on Attention Mechanism and Improved Loss Function

Contact Info

Product

Resources

About