ultralytics/yolov5: v3.1 - Bug Fixes and Performance Improvements

Jocher, Glenn; Stoken, Alex; Borovec, Jirka; NanoCode,; ChristopherSTAN,; Liu, Changyu; Laughing,; tkianai,; Hogan, Adam; lorenzomammana,; yxNONG,; AlexWang,; Diaconu, Laurentiu; Marc,; wanghaoyang,; ah, ml; Doug,; Ingham, Francisco; Frederik,; Guilhen,; Hatovix,; Poznanski, Jake; Fang, Jiacong; 于力军, Lijun Yu; changyu,; Wang, Mingyu; Gupta, Deepak; Akhtar, Osama; PetrDvoracek,; Rai, Prashant

doi:10.5281/zenodo.4154370

Cited by 158 publications

(109 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…the model is tested using training data and would give biased results. [20]. Additionally, the difference between the maximum and minimum cat images varies greatly, i.e.…”

Section: Data and Methodology 31 Datasetmentioning

confidence: 99%

“…This significantly improves the efficiency of model training [16]. Mosaic augmentation algorithms work well in certain domains such as aerial imagery where target objects may appear at any position within the images [20]. It can create synthetic training data for objects in different contexts and thus enhance the robustness of the model.…”

Section: Augmentation Methodsmentioning

confidence: 99%

“…As such, we use YOLOv5 as the initial base model to perform the feral cat detection experiments. The YOLOv5 implementation we applied in this work was adapted from its original version [20].…”

Section: Base Model Selectionmentioning

confidence: 99%

“…Specifically, in this paper we apply the latest version of the You Only Look Once version 5 (YOLOv5) detection model [20] to image data obtained from temperature-in-motion sensing camera-traps for individual feral cat identification. We explore the application of various image pre-processing and data augmentation methods and highlight the enormous improvements in accuracy that can be obtained through advanced image augmentation techniques.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Individual Feral Cat Identification through Deep Learning

Yang

Sinnott

et al. 2021

2021 IEEE/ACM 8th International Conference on Big Data Computing, Applications and Technologies (BDCAT '21)

View full text Add to dashboard Cite

Computer vision opportunities based on deep learning have seen an increasing trend in recent years through the proliferation of convolutional neural networks (CNN) and related deep learning models. However, limited training data often constrains the performance and accuracy of such models -this is a common situation for many detection and classification tasks especially in the ecological field. In this paper, we present a case study of how one such model: You Only Look Once (YOLO) version 5 can be applied to individual feral cat identification using a small unbalanced data set. We describe the procedures for preparing the training and validation data set, training the model using data augmentation and transfer learning techniques, and testing the model on both in-distribution and out-of-distribution samples. We explore the effectiveness of data augmentation methods including basic image manipulations and more advanced augmentation techniques that are now available.

show abstract

“…the model is tested using training data and would give biased results. [20]. Additionally, the difference between the maximum and minimum cat images varies greatly, i.e.…”

Section: Data and Methodology 31 Datasetmentioning

confidence: 99%

Section: Augmentation Methodsmentioning

confidence: 99%

Section: Base Model Selectionmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Individual Feral Cat Identification through Deep Learning

Yang

Sinnott

et al. 2021

2021 IEEE/ACM 8th International Conference on Big Data Computing, Applications and Technologies (BDCAT '21)

View full text Add to dashboard Cite

show abstract

“…1) Object Detection: The object detection application is implemented through YOLOv5s [41] trained on the COCO data set [42]. The algorithm divides images into a grid system, where each cell in the grid is responsible for detecting objects within itself.…”

Section: A Vehicular Applicationsmentioning

confidence: 99%

Data-Driven Capacity Planning for Vehicular Fog Computing

Mao¹,

Akgül²,

Mehrabidavoodabadi³

et al. 2022

Preprint

View full text Add to dashboard Cite

The strict latency constraints of emerging vehicular applications make it unfeasible to forward sensing data from vehicles to the cloud for processing. To shorten network latency, Vehicular fog computing (VFC) moves computation to the edge of the Internet, with the extension to support the mobility of distributed computing entities. In other words, VFC proposes to complement stationary fog nodes co-located with cellular base stations with mobile ones carried by moving vehicles. Previous works of VFC mainly focus on optimizing the assignments of computing tasks among available fog nodes. However, capacity planning, which decides where and how much capacity to deploy, remains an open and challenging issue. The complexity of this problem comes from the mobility of vehicles, the spatio-temporal dynamics of vehicular traffic, and the computing resource demand generated by varying vehicular applications. To solve the above challenges, we propose a data-driven capacity planning framework that optimizes the deployment of stationary and mobile fog nodes to minimize the installation and operational costs under the quality-of-service constraints, taking into account the spatio-temporal variation in computing demand. Through real-world experiments, we analyze the cost efficiency potential of VFC in long term and demonstrate that the performance loss of VFC is below $6\%$ compared to stationary deployment with equal network capacity. We also analyze the impacts of traffic patterns on the potential cost saving. The results show when the traffic density is higher, more operational costs will be saved in the long run due to more dense deployment of mobile fog nodes.

show abstract

A Wearable Device Integrated with Deep Learning‐Based Algorithms for the Analysis of Breath Patterns

Tarim,

Erimez,

Degirmenci

et al. 2023

Advanced Intelligent Systems

View full text Add to dashboard Cite

Sleep problems are serious issues that make life difficult for all people, including sleep apnea. Sleep apnea, which causes breathlessness for more than 10 s, is linked to severe health problems due to the serious damage it can induce. To mitigate the risk of these disorders, the monitoring of patients has become increasingly challenging. Wearable technologies offer an effective healthcare solution for remote patient monitoring and diagnosis. A novel wearable system based on Arduino technology is introduced, specifically designed to monitor the breath patterns of patients. The analysis of breath data from patients holds great importance for the diagnosis and continuous monitoring of sleep apnea. To address this need, an advanced image processing system based on deep learning techniques is presented. This system automatically detects respiratory patterns, including inhalation, exhalation, and breathlessness. The device has an average of 97.6% sensitivity, 79.7% specificity, and 96% accuracy in identifying breath patterns. The designed device can offer patients and healthcare institutions a simple, inexpensive, noninvasive, and ergonomic system for the analysis of breath patterns that can be further extended for sleep apnea diagnosis.

show abstract

ultralytics/yolov5: v3.1 - Bug Fixes and Performance Improvements

Cited by 158 publications

References 0 publications

Individual Feral Cat Identification through Deep Learning

Individual Feral Cat Identification through Deep Learning

Data-Driven Capacity Planning for Vehicular Fog Computing

A Wearable Device Integrated with Deep Learning‐Based Algorithms for the Analysis of Breath Patterns

Contact Info

Product

Resources

About