Review of Deep Learning Based Object Detection Methods and Their Mainstream Frameworks

Zhongjing, 段仲静 Duan; Shaobo, 李少波 Li; Jianjun, 胡建军 Hu; Yang, Jing; Zheng, 王铮 Wang

doi:10.3788/lop57.120005

Cited by 14 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning, a branch of machine learning, is a frontier for artificial intelligence, aiming to be closer to its primary goal-artificial intelligence. At present, there are two widely used target detection algorithms based on deep learning: two-stage detection based on candidate regions and singlestage detection based on regression [16][17][18][19][20]. The former includes R-CNN and faster R-CNN.…”

Section: Literature Reviewmentioning

confidence: 99%

“…As an excellent target detection algorithm at present, Yolox algorithm has the advantage that the type and speed of target detection have been greatly improved [17][18][19][20]. The aviation rivet classification and anomaly detection algorithm based on deep learning are improved on the basis of Yolox algorithm.…”

Section: Target Detection Algorithm Of Aviation Rivetmentioning

confidence: 99%

See 1 more Smart Citation

Aviation Rivet Classification and Anomaly Detection Based on Deep Learning

Zhu

2023

International Journal of Aerospace Engineering

View full text Add to dashboard Cite

The shortage of personnel and the high cost have become a major pain point in the current safety supervision work of the inspectors. Aiming at the problem that the aircraft maintenance inspector could not visit the scene in person during the epidemic, a remote safety supervision platform was built based on intelligent glasses and 5G network, and the real-time monitoring of the aircraft skin rivet status was realized. And a method of aviation rivet classification and anomaly detection based on deep learning algorithm was proposed. Firstly, according to the appearance of rivet head, the aviation rivet is classified, the data set of aviation rivet is made, and the aviation rivet classification and anomaly detection model are constructed. Evaluate the detection results from such indicators as confidence, precision, recall rate, and mAP and compare the algorithm with the detection results of Yolox-s, Yolox-m, Yolov5-s, Yolov5-m, and Yolov4. The results show that (1) the algorithm proposed in this paper can realize the classification of aviation rivets and the detection of abnormal conditions, the confidence of the detection results is more than 90%, and the average precision, recall, and AP value are above 95%, 85%, and 88%, respectively. (2) The order of rivet classification and abnormal detection effect from good to bad is Philips screws, round head rivets, flat head rivets, countersunk head rivets, blind rivets, and abnormal condition. (3) Compared with other algorithms, the aviation rivet classification abnormal target detection based on deep learning has absolute advantages in accuracy and speed.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Target Detection Algorithm Of Aviation Rivetmentioning

confidence: 99%

Aviation Rivet Classification and Anomaly Detection Based on Deep Learning

Zhu

2023

International Journal of Aerospace Engineering

View full text Add to dashboard Cite

show abstract

“…With the development of deep learning in object detection, the target detection network is widely used for foreground extraction and anomaly detection [5]. Duan use the YOLOv3 target detection network to detect pedestrians with sicks, guns, and knives [6].…”

Section: Figure 1 Anomaly Detection Processmentioning

confidence: 99%

Comparative analysis of video anomaly detection algorithms

Cheng

Yuan

Liu

et al. 2022

International Conference on Computer, Artificial Intelligence, and Control Engineering (CAICE 2022)

View full text Add to dashboard Cite

With the continuous development of deep learning, anomaly detection technology in computer vision has maderemarkable progress. Video anomaly detection is essential to ensure public safety. We classify and summarize anomalydetection based on deep learning. First, the overall process of anomaly detection is presented. Then, based on the neural network training method, we discuss the development and application of deep learning in the field of anomaly detectionfrom four aspects: Multiple Instance Learning, Regression models, Clustering models, and Reconstruction models. Finally, we present commonly used datasets and performance evaluation criteria , analyze the performance of different algorithms and discuss the future directions.

show abstract

“…In recent years, the target detection algorithms based on convolutional neural networks (CNN) have been developing continuously. These algorithms can be generally divided into: two step target detection algorithms and one step target detection algorithm based on regression [4]. The two-stage detection algorithm first generates candidate regions through the regional candidate network (RPN), and then performs classification and regression, that is, the location and classification results are obtained successively through two stages, such as Faster R-CNN [5], R-FCN [8], etc.…”

Section: Introductionmentioning

confidence: 99%

Target detection algorithm based on super- resolution color remote sensing image reconstruction

Wang,

Chen

et al. 2023

J. meas. eng.

View full text Add to dashboard Cite

An improved generative adversarial network model is adopted to improve the resolution of remote sensing images and the target detection algorithm for color remote sensing images. The main objective is to solve the problem of training super-resolution reconstruction algorithms and missing details in reconstructed images, aiming to achieve high-precision detection of medium and low-resolution color remote sensing targets. First, a lightweight image super-resolution reconstruction algorithm based on an improved generative adversarial network (GAN) is proposed. This algorithm combines the pixel attention mechanism and up-sampling method to restore image details. It further integrates edge-oriented convolution modules into traditional convolution to reduce model parameters and achieve better feature collection. Then, to further enhance the feature collection ability of the model, the YOLOv4 object detection algorithm is also improved. This is achieved by introducing the Focus structure into the backbone feature extraction network and integrating multi-layer separable convolutions to improve the feature extraction ability. The experimental results show that the improved target detection algorithm based on super resolution has a good detection effect on remote sensing image targets. It can effectively improve the detection accuracy of remote sensing images, and have a certain reference significance for the realization of small target detection in remote sensing images.

show abstract

Review of Deep Learning Based Object Detection Methods and Their Mainstream Frameworks

Cited by 14 publications

References 0 publications

Aviation Rivet Classification and Anomaly Detection Based on Deep Learning

Aviation Rivet Classification and Anomaly Detection Based on Deep Learning

Comparative analysis of video anomaly detection algorithms

Target detection algorithm based on super- resolution color remote sensing image reconstruction

Contact Info

Product

Resources

About