Performance Comparison of Moving Target Recognition between Faster R-CNN and SSD

Jin, Hongyu; Yan, Ming; Lu, Jinyu; Zhu, Lingyao; Wang, Kaili; Bai, Shilei

doi:10.1109/ijcime49369.2019.00018

Cited by 5 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the beginning, an image will be firstly scaled to a fixed size M × N and passed to the convolutional network. In this paper, we would use the VGG network as the backbone [11]. The original VGG network includes convolutional layers and fully connected (FC) layers [11].…”

Section: Faster R-cnnmentioning

confidence: 99%

See 1 more Smart Citation

Performance Evaluation of Ship Target Detection Algorithms Based on Deep Learning

2023

AJETS

View full text Add to dashboard Cite

Ship target detection plays an important role in marine military and shipping. Deep learning allows us to extract deep features from large amount of data. In this paper, we select three different target detection algorithms based on deep learning, including Faster R-CNN, SSD, and YOLOv3, and apply the same dataset to these three algorithms. Then compare the results of the experiments and evaluate the performance of each algorithm. According to the result of the experiments, Faster R-CNN has a relatively better performance. The result of this paper would provide a reference for selecting a ship target detection algorithm.

show abstract

Section: Faster R-cnnmentioning

confidence: 99%

“…In this paper, we would use the VGG network as the backbone [11]. The original VGG network includes convolutional layers and fully connected (FC) layers [11]. But in Faster R-CNN, the convolutional layers are used to extract the feature map from the picture, only the convolutional layers would be used [10].…”

Section: Faster R-cnnmentioning

confidence: 99%

Performance Evaluation of Ship Target Detection Algorithms Based on Deep Learning

2023

AJETS

View full text Add to dashboard Cite

show abstract

“…The current target detection algorithms based on deep learning are roughly divided into deep learning target detection algorithms based on regions of interest and deep learning target detection algorithms based on regression. Among them, deep learning target detection algorithms based on regions of interest include RCNN [14,15], SPP-net [16,17], Fast RCNN [18,19], Faster RCNN [20,21], Mask R-CNN [22][23][24][25], and YOLO [26,27].…”

Section: Introductionmentioning

confidence: 99%

Single Shot Multibox Detector Automatic Polyp Detection Network Based on Gastrointestinal Endoscopic Images

Chen

Zhang

Lin

et al. 2021

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

Purpose. In order to resolve the situation of high missed diagnosis rate and high misdiagnosis rate of the pathological analysis of the gastrointestinal endoscopic images by experts, we propose an automatic polyp detection algorithm based on Single Shot Multibox Detector (SSD). Method. In the paper, SSD is based on VGG-16, the fully connected layer is changed to a convolutional layer, and four convolutional layers with successively decreasing scales are added as a new network structure. In order to verify the practicability, it is not only compared with manual polyp detection but also with Mask R-CNN. Results. Multiple experimental results show that the mean Average Precision (mAP) of the SSD network is 95.74%, which is 12.4% higher than the manual detection and 5.7% higher than the Mask R-CNN. When detecting a single frame of image, the detection speed of SSD is 8.41 times that of manual detection. Conclusion. Based on the traditional pattern recognition algorithm and the target detection algorithm using deep learning, we select a variety of algorithms to identify and classify polyps to achieve efficient detection results. Our research demonstrates that deep learning has a lot of room for development in the field of gastrointestinal image recognition.

show abstract

Detection and Classification of Incoming Ambulance Vehicle using Artificial Intelligence Technology

Sarapirom

Poochaya

2021

2021 18th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technolo

View full text Add to dashboard Cite

Performance Comparison of Moving Target Recognition between Faster R-CNN and SSD

Cited by 5 publications

References 14 publications

Performance Evaluation of Ship Target Detection Algorithms Based on Deep Learning

Performance Evaluation of Ship Target Detection Algorithms Based on Deep Learning

Single Shot Multibox Detector Automatic Polyp Detection Network Based on Gastrointestinal Endoscopic Images

Detection and Classification of Incoming Ambulance Vehicle using Artificial Intelligence Technology

Contact Info

Product

Resources

About