RetinaNet-Based Approach for Object Detection and Distance Estimation in an Image

Alhasanat, Mohanad; Alsafasfeh, Moath; Alhasanat, Abdullah E.; Althunibat, Saud

doi:10.15866/irecap.v11i1.19341

Cited by 4 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To find an accurate algorithm that can detect objects using thermal infrared images, we analysed different object detectors based on their performance parameters. Faster R-CNN, MRCNN [4], HOG [8] , YOLO V3 [9] , YOLO V8, SSD [10], RetinaNet [7] achieved best results for object detection. We selected one stage detectors, namely YOLO, SSD and RetinaNet, as they have high inference speeds [3].…”

Section: Methodsmentioning

confidence: 99%

Performance Analysis: Object Detection System for Low Illumination

Balasaheb,

Sanjay,

Somnath

et al. 2024

IJRASET

View full text Add to dashboard Cite

Abnormal activity detection plays a very important role in surveillance applications. The existing research on surveillance for daytime has achieved better performance by detecting and tracking objects using deep learning algorithms. However, it is difficult to achieve the same performance for night vision mainly due to low illumination. Deep learning is a powerful machine learning technique in which the object detector automatically learns image features required for detection tasks. It is required to generate a model that detects objects under low illumination. The approach is to use thermal infrared images and detect external objects, if any, and classify whether it is human or animal in an isolation area. With the rapid growth of deep learning, more efficient techniques will be implemented to solve the problems of object detection using neural networks and deep learning

show abstract

Section: Methodsmentioning

confidence: 99%

Performance Analysis: Object Detection System for Low Illumination

Balasaheb,

Sanjay,

Somnath

et al. 2024

IJRASET

View full text Add to dashboard Cite

show abstract

“…RetinaNet ( Fig 1B ) [ 54 ] is a single-stage object detector a with feature pyramid network to detect small and dense objects. In a single stage architecture, the training procedure is dominated by easily classified background examples and it leads to the learning of foreground examples difficult.…”

Section: Methodsmentioning

confidence: 99%

A comparison of machine learning approaches for the quantification of microglial cells in the brain of mice, rats and non-human primates

et al. 2023

View full text Add to dashboard Cite

Microglial cells are brain-specific macrophages that swiftly react to disruptive events in the brain. Microglial activation leads to specific modifications, including proliferation, morphological changes, migration to the site of insult, and changes in gene expression profiles. A change in inflammatory status has been linked to many neurodegenerative diseases such as Parkinson’s disease and Alzheimer’s disease. For this reason, the investigation and quantification of microglial cells is essential for better understanding their role in disease progression as well as for evaluating the cytocompatibility of novel therapeutic approaches for such conditions. In the following study we implemented a machine learning-based approach for the fast and automatized quantification of microglial cells; this tool was compared with manual quantification (ground truth), and with alternative free-ware such as the threshold-based ImageJ and the machine learning-based Ilastik. We first trained the algorithms on brain tissue obtained from rats and non-human primate immunohistochemically labelled for microglia. Subsequently we validated the accuracy of the trained algorithms in a preclinical rodent model of Parkinson’s disease and demonstrated the robustness of the algorithms on tissue obtained from mice, as well as from images provided by three collaborating laboratories. Our results indicate that machine learning algorithms can detect and quantify microglial cells in all the three mammalian species in a precise manner, equipotent to the one observed following manual counting. Using this tool, we were able to detect and quantify small changes between the hemispheres, suggesting the power and reliability of the algorithm. Such a tool will be very useful for investigation of microglial response in disease development, as well as in the investigation of compatible novel therapeutics targeting the brain. As all network weights and labelled training data are made available, together with our step-by-step user guide, we anticipate that many laboratories will implement machine learning-based quantification of microglial cells in their research.

show abstract

“…The model divides the image according to a grid and within each grid cell detects objects, predicting their class and location. RetinaNet is a one-stage object detection model (Alhasanat et al 2021), often applied to aerial and satellite imagery, and has a high true-positive rate for small-scale objects. RetinaNet also uses a ResNet as a backbone network, but uses Focal Loss as an enhancement over Cross-Entropy Loss to handle the class imbalance problem.…”

Section: Methodsmentioning

confidence: 99%

Multidisciplinary digital methodologies for documentation and preservation of immovable Archaeological heritage in the Khovd River Valley, Western Mongolia

et al. 2022

View full text Add to dashboard Cite

Background: The archaeological and ethnographic heritages of Mongolia reflect a multi-millennial continuity of typically mobile-pastoral occupations across sparsely populated, environmentally diverse landscapes, but the threats of modernisation and industrialisation to those heritages are nevertheless present and substantial. The construction of the Erdeneburen Hydroelectric Dam on the Khovd River in western Mongolia is planned to submerge hundreds of archaeological features and jeopardise at least another thousand. Methods: The Mongolian Archaeology Project: Surveying the Steppes, in collaboration with the Mongolian Institute of Archaeology, integrates a variety of digital techniques including GIS (geographic information systems), Machine Learning automated site detection, drone mapping, and Structure-from-Motion LiDAR scanning to document the endangered archaeology. This paper presents the resulting dataset of archaeological features across three different impact zones associated with the dam construction and evaluates the degree of efficacy of the initial data integration strategy through informal partner feedback and self-assessment. Results: While only approximately 20% of the documented sites fall within the planned flood zone, the remaining sites will be subjected to collateral threats such as industrial and infrastructural development that will necessitate extended monitoring, both temporally and spatially. In consideration of these results, this paper argues that a ‘responsive’ mode of heritage disaster intervention can bridge the gap between ‘reactive’ and ‘proactive’ modes, but requires development of an integrated (digital) methodology. Conclusions: The paper concludes by offering a new, more interconnected ‘transmethodology’ that addresses spatiality, sub-sampling, data reuse, and community input across multiple disciplines such as cultural heritage preservation, salvage archaeology, computer vision, and community archaeology. The authors developed this ‘transmethodology’ and the resulting workflows out of a theoretical framework that considers principles of Symmetrical Archaeology, Resilience Humanitarianism, and the CARE standard for inclusive data management (Collective benefit, Authority to control, Responsibility, and Ethics).

show abstract

RetinaNet-Based Approach for Object Detection and Distance Estimation in an Image

Cited by 4 publications

References 0 publications

Performance Analysis: Object Detection System for Low Illumination

Performance Analysis: Object Detection System for Low Illumination

A comparison of machine learning approaches for the quantification of microglial cells in the brain of mice, rats and non-human primates

Multidisciplinary digital methodologies for documentation and preservation of immovable Archaeological heritage in the Khovd River Valley, Western Mongolia

Contact Info

Product

Resources

About