Light-Weight RetinaNet for Object Detection on Edge Devices

Li, Yixing; Dua, Akshay; Ren, Fengbo

doi:10.1109/wf-iot48130.2020.9221150

Cited by 25 publications

(15 citation statements)

References 16 publications

(38 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As we know, the one-stage, CNN-based object-detection method, Reti-naNet [27] with a novel loss function, can not only detect objects but also reduce the impact of class imbalance on object classification. From the view of object-detection performance, RetinaNet outperforms SSD, YOLOv2, and YOLOv3 for the COCO dataset [28]. From the view of computation complexity, an object-detection network usually has higher computational complexity compared with an image classification network [28].…”

Section: System Descriptionmentioning

confidence: 99%

“…From the view of object-detection performance, RetinaNet outperforms SSD, YOLOv2, and YOLOv3 for the COCO dataset [28]. From the view of computation complexity, an object-detection network usually has higher computational complexity compared with an image classification network [28]. For one-stage object-detection networks, RetinaNet is superior to YOLOv3 in terms of FLOPs (floatingpoint operation) and mAP (mean average precision) for object detection [28].…”

Section: System Descriptionmentioning

confidence: 99%

“…From the view of computation complexity, an object-detection network usually has higher computational complexity compared with an image classification network [28]. For one-stage object-detection networks, RetinaNet is superior to YOLOv3 in terms of FLOPs (floatingpoint operation) and mAP (mean average precision) for object detection [28]. This means that RetinaNet is a better choice of object detection in terms of computational complexity and object-detection performance.…”

Section: System Descriptionmentioning

confidence: 99%

“…It is expected that the higher the IoU is, the better the performance will be. In fact, IoU is usually used when computing mAP [1,28] for performance evaluation of object detection. Next, we explain the performance indices of recognizing key characters used in the experiment.…”

Section: Performance Indexmentioning

confidence: 99%

“…Here, average precision (AP) is also exploited. Furthermore, since there are some key characters that should be detected in document images, mAP [1,28] is also utilized to evaluate whether a scheme can simultaneously detect these key characters successfully. It is expected that the higher the mAP is, the better the performance will be.…”

Section: Performance Indexmentioning

confidence: 99%

See 4 more Smart Citations

Keyword Detection Based on RetinaNet and Transfer Learning for Personal Information Protection in Document Images

Lin

2021

Applied Sciences

View full text Add to dashboard Cite

In this paper, a keyword detection scheme is proposed based on deep convolutional neural networks for personal information protection in document images. The proposed scheme is composed of key character detection and lexicon analysis. The first part is the key character detection developed based on RetinaNet and transfer learning. To find the key characters, RetinaNet, which is composed of convolutional layers featuring a pyramid network and two subnets, is exploited to detect key characters within the region of interest in a document image. After the key character detection, the second part is a lexicon analysis, which analyzes and combines several key characters to find the keywords. To train the model of RetinaNet, synthetic image generation and data augmentation are exploited to yield a large image dataset. To evaluate the proposed scheme, many document images are selected for testing, and two performance measurements, IoU (Intersection Over Union) and mAP (Mean Average Precision), are used in this paper. Experimental results show that the mAP rates of the proposed scheme are 85.1% and 85.84% for key character detection and keyword detection, respectively. Furthermore, the proposed scheme is superior to Tesseract OCR (Optical Character Recognition) software for detecting the key characters in document images. The experimental results demonstrate that the proposed method can effectively localize and recognize these keywords within noisy document images with Mandarin Chinese words.

show abstract

Section: System Descriptionmentioning

confidence: 99%

Section: System Descriptionmentioning

confidence: 99%

Section: System Descriptionmentioning

confidence: 99%

Section: Performance Indexmentioning

confidence: 99%

Section: Performance Indexmentioning

confidence: 99%

See 3 more Smart Citations

Keyword Detection Based on RetinaNet and Transfer Learning for Personal Information Protection in Document Images

Lin

2021

Applied Sciences

View full text Add to dashboard Cite

show abstract

MFF‐Net: Multiscale feature fusion semantic segmentation network for intracranial surgical instruments

Liu,

Zheng,

Yang

et al. 2023

Robotics Computer Surgery

View full text Add to dashboard Cite

BackgroundIn robot‐assisted surgery, automatic segmentation of surgical instrument images is crucial for surgical safety. The proposed method addresses challenges in the craniotomy environment, such as occlusion and illumination, through an efficient surgical instrument segmentation network.MethodsThe network uses YOLOv8 as the target detection framework and integrates a semantic segmentation head to achieve detection and segmentation capabilities. A concatenation of multi‐channel feature maps is designed to enhance model generalisation by fusing deep and shallow features. The innovative GBC2f module ensures the lightweight of the network and the ability to capture global information.ResultsExperimental validation of the intracranial glioma surgical instrument dataset shows excellent performance: 94.9% MPA score, 89.9% MIoU value, and 126.6 FPS.ConclusionsAccording to the experimental results, the segmentation model proposed in this study has significant advantages over other state‐of‐the‐art models. This provides a valuable reference for the further development of intelligent surgical robots.

show abstract

Using photographs and deep neural networks to understand flowering phenology and diversity in mountain meadows

John,

Theobald,

Cristea

et al. 2024

Remote Sens Ecol Conserv

View full text Add to dashboard Cite

Mountain meadows are an essential part of the alpine–subalpine ecosystem; they provide ecosystem services like pollination and are home to diverse plant communities. Changes in climate affect meadow ecology on multiple levels, for example, by altering growing season dynamics. Tracking the effects of climate change on meadow diversity through the impacts on individual species and overall growing season dynamics is critical to conservation efforts. Here, we explore how to combine crowd‐sourced camera images with machine learning to quantify flowering species richness across a range of elevations in alpine meadows located in Mt. Rainier National Park, Washington, USA. We employed three machine‐learning techniques (Mask R‐CNN, RetinaNet and YOLOv5) to detect wildflower species in images taken during two flowering seasons. We demonstrate that deep learning techniques can detect multiple species, providing information on flowering richness in photographed meadows. The results indicate higher richness just above the tree line for most of the species, which is comparable with patterns found using field studies. We found that the two‐stage detector Mask R‐CNN was more accurate than single‐stage detectors like RetinaNet and YOLO, with the Mask R‐CNN network performing best overall with mean average precision (mAP) of 0.67 followed by RetinaNet (0.5) and YOLO (0.4). We found that across the methods using anchor box variations in multiples of 16 led to enhanced accuracy. We also show that detection is possible even when pictures are interspersed with complex backgrounds and are not in focus. We found differential detection rates depending on species abundance, with additional challenges related to similarity in flower characteristics, labeling errors and occlusion issues. Despite these potential biases and limitations in capturing flowering abundance and location‐specific quantification, accuracy was notable considering the complexity of flower types and picture angles in this dataset. We, therefore, expect that this approach can be used to address many ecological questions that benefit from automated flower detection, including studies of flowering phenology and floral resources, and that this approach can, therefore, complement a wide range of ecological approaches (e.g., field observations, experiments, community science, etc.). In all, our study suggests that ecological metrics like floral richness can be efficiently monitored by combining machine learning with easily accessible publicly curated datasets (e.g., Flickr, iNaturalist).

show abstract

Light-Weight RetinaNet for Object Detection on Edge Devices

Cited by 25 publications

References 16 publications

Keyword Detection Based on RetinaNet and Transfer Learning for Personal Information Protection in Document Images

Keyword Detection Based on RetinaNet and Transfer Learning for Personal Information Protection in Document Images

MFF‐Net: Multiscale feature fusion semantic segmentation network for intracranial surgical instruments

Using photographs and deep neural networks to understand flowering phenology and diversity in mountain meadows

Contact Info

Product

Resources

About