A Review of Yolo Algorithm Developments

Jiang, Peiyuan; Ergu, Daji; Liu, Fangyao; Cai, Ying; Ma, Bo

doi:10.1016/j.procs.2022.01.135

Cited by 985 publications

(448 citation statements)

References 13 publications

Supporting

Mentioning

241

Contrasting

Unclassified

Order By: Relevance

“…However, the two small bounding-boxes in the front and rear were very similar. Therefore, YOLO was not the best performance for similar objects in one image [ 83 ]. The low performance is caused by the fact that just two small boxes in the grid are anticipated and only belong to a new class of objects within the same category, resulting in an abnormal aspect ratio and other factors such as low generalization capacity [ 84 ].…”

Section: Discussionmentioning

confidence: 99%

A Deep Learning Method for Foot Progression Angle Detection in Plantar Pressure Images

Ardhianto

Subiakto

Lin

et al. 2022

Sensors

View full text Add to dashboard Cite

Foot progression angle (FPA) analysis is one of the core methods to detect gait pathologies as basic information to prevent foot injury from excessive in-toeing and out-toeing. Deep learning-based object detection can assist in measuring the FPA through plantar pressure images. This study aims to establish a precision model for determining the FPA. The precision detection of FPA can provide information with in-toeing, out-toeing, and rearfoot kinematics to evaluate the effect of physical therapy programs on knee pain and knee osteoarthritis. We analyzed a total of 1424 plantar images with three different You Only Look Once (YOLO) networks: YOLO v3, v4, and v5x, to obtain a suitable model for FPA detection. YOLOv4 showed higher performance of the profile-box, with average precision in the left foot of 100.00% and the right foot of 99.78%, respectively. Besides, in detecting the foot angle-box, the ground-truth has similar results with YOLOv4 (5.58 ± 0.10° vs. 5.86 ± 0.09°, p = 0.013). In contrast, there was a significant difference in FPA between ground-truth vs. YOLOv3 (5.58 ± 0.10° vs. 6.07 ± 0.06°, p < 0.001), and ground-truth vs. YOLOv5x (5.58 ± 0.10° vs. 6.75 ± 0.06°, p < 0.001). This result implies that deep learning with YOLOv4 can enhance the detection of FPA.

show abstract

Section: Discussionmentioning

confidence: 99%

A Deep Learning Method for Foot Progression Angle Detection in Plantar Pressure Images

Ardhianto

Subiakto

Lin

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…This is a unified model for object detection which is trained on a loss function that directly corresponds to detection performance, and the entire model is trained jointly [ 35 ]. In recent years, five versions of YOLO have been released, each time with significant changes in the algorithm structure that improved both the inference time and the accuracy of the algorithm [ 36 ]. In terms of inference time and detection accuracy, YOLO was used in this work mainly because of the need to automate the process of classifying iRAP road segments which requires a fast inference time.…”

Section: Methodsmentioning

confidence: 99%

Automatic Roadside Feature Detection Based on Lidar Road Cross Section Images

Brkić

Miler

Ševrović

et al. 2022

Sensors

View full text Add to dashboard Cite

The United Nations (UN) stated that all new roads and 75% of travel time on roads must be 3+ star standard by 2030. The number of stars is determined by the International Road Assessment Program (iRAP) star rating module. It is based on 64 attributes for each road. In this paper, a framework for highly accurate and fully automatic determination of two attributes is proposed: roadside severity-object and roadside severity-distance. The framework integrates mobile Lidar point clouds with deep learning-based object detection on road cross-section images. The You Only Look Once (YOLO) network was used for object detection. Lidar data were collected by vehicle-mounted mobile Lidar for all Croatian highways. Point clouds were collected in .las format and cropped to 10 m-long segments align vehicle path. To determine both attributes, it was necessary to detect the road with high accuracy, then roadside severity-distance was determined with respect to the edge of the detected road. Each segment is finally classified into one of 13 roadside severity object classes and one of four roadside severity-distance classes. The overall accuracy of the roadside severity-object classification is 85.1%, while for the distance attribute it is 85.6%. The best average precision is achieved for safety barrier concrete class (0.98), while the worst AP is achieved for rockface class (0.72).

show abstract

“…It is easy to implement and can train the entire image immediately. For this reason, YOLO has developed gradually [25]. In 2020, the fifth version of YOLO was released.…”

Section: Yolov5_ours Networkmentioning

confidence: 99%

Improved YOLOv5: Efficient Object Detection Using Drone Images under Various Conditions

2022

View full text Add to dashboard Cite

With the recent development of drone technology, object detection technology is emerging, and these technologies can also be applied to illegal immigrants, industrial and natural disasters, and missing people and objects. In this paper, we would like to explore ways to increase object detection performance in these situations. Photography was conducted in an environment where it was confusing to detect an object. The experimental data were based on photographs that created various environmental conditions, such as changes in the altitude of the drone, when there was no light, and taking pictures in various conditions. All the data used in the experiment were taken with F11 4K PRO drone and VisDrone dataset. In this study, we propose an improved performance of the original YOLOv5 model. We applied the obtained data to each model: the original YOLOv5 model and the improved YOLOv5_Ours model, to calculate the key indicators. The main indicators are precision, recall, F-1 score, and mAP (0.5), and the YOLOv5_Ours values of mAP (0.5) and function loss were improved by comparing it with the original YOLOv5 model. Finally, the conclusion was drawn based on the data comparing the original YOLOv5 model and the improved YOLOv5_Ours model. As a result of the analysis, we were able to arrive at a conclusion on the best model of object detection under various conditions.

show abstract

A Review of Yolo Algorithm Developments

Cited by 985 publications

References 13 publications

A Deep Learning Method for Foot Progression Angle Detection in Plantar Pressure Images

A Deep Learning Method for Foot Progression Angle Detection in Plantar Pressure Images

Automatic Roadside Feature Detection Based on Lidar Road Cross Section Images

Improved YOLOv5: Efficient Object Detection Using Drone Images under Various Conditions

Contact Info

Product

Resources

About