ultralytics/yolov5: v5.0 - YOLOv5-P6 1280 models, AWS, Supervise.ly and YouTube integrations

Jocher, Glenn; Stoken, Alex; Borovec, Jirka; NanoCode,; Chaurasia, Ayush; TaoXie,; Liu, Changyu; Abhiram,; Laughing,; tkianai,; yxNONG,; Hogan, Adam; lorenzomammana,; AlexWang,; Hájek, Jan; Diaconu, Laurentiu; Marc,; Kwon, Yonghye; Олег,; wanghaoyang,; Defretin, Yann; Lohia, Aditya; ah, ml; Milanko, Ben; Fineran, Benjamin; Khromov, Daniel; Yiwei, Ding; Doug,; Durgesh,; Ingham, Francisco

doi:10.5281/zenodo.4679653

Cited by 113 publications

(82 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In order to calculate safety metrics, we need to extract motion trajectories of vehicles from the video files. To this end, we integrate a tracking algorithm called simple online and realtime tracking with deep association metric (DeepSORT) [78] with the you only look once (YOLO)-v5 [22] detector to obtain trajectories of labeled objects. DeepSORT is a real-time multiobject tracking algorithm based on Kalman filtering and Hungarian algorithm, which can consider both bounding box parameters and appearance simultaneously.…”

Section: Video Preprocessingmentioning

confidence: 99%

“…The community also benefits from the recent developments in image/video processing using deep learning (DL) methods with superior performance far beyond the conventional methods. DL methods have also enabled developing wellannotated volume datasets, such as the highD dataset (2018) [18] that accelerate the pace of discovery in developing even more powerful video processing methods such as YOLO series [19,20,21,22] and RCNN family [23,24,25,26,27]) for object detection and tracking.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Network-level Safety Metrics for Overall Traffic Safety Assessment: A Case Study

Chen¹,

Wang²,

Razi³

et al. 2022

Preprint

View full text Add to dashboard Cite

Driving safety analysis has recently witnessed unprecedented results due to advances in computation frameworks, connected vehicle technology, new generation sensors, and artificial intelligence (AI). Particularly, the recent advances performance of deep learning (DL) methods realized higher levels of safety for autonomous vehicles and empowered volume imagery processing for driving safety analysis. An important application of DL methods is extracting driving safety metrics from traffic imagery. However, the majority of current methods use safety metrics for micro-scale analysis of individual crash incidents or near-crash events, which does not provide insightful guidelines for the overall network-level traffic management. On the other hand, large-scale safety assessment efforts mainly emphasize spatial and temporal distributions of crashes, while not always revealing the safety violations that cause crashes. To bridge these two perspectives, we define a new set of network-level safety metrics for the overall safety assessment of traffic flow by processing imagery taken by roadside infrastructure sensors. An integrative analysis of the safety metrics and crash data reveals the insightful temporal and spatial correlation between the representative network-level safety metrics and the crash frequency. The analysis is performed using two video cameras in the state of Arizona along with a 5-year crash report obtained from the Arizona Department of Transportation. The results confirm that network-level safety metrics can be used by the traffic management teams to equip traffic monitoring systems with advanced AI-based risk analysis, and timely traffic flow control decisions.

show abstract

Section: Video Preprocessingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Network-level Safety Metrics for Overall Traffic Safety Assessment: A Case Study

Chen¹,

Wang²,

Razi³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Yolov5 [62] is a state of the art implementation of the Yolo object detection model implemented with multiple improvements to the Yolo framework that have been found in recent years. In this work, we used the unmodified YOLOv5m6 implementation of Yolov5 in release v5.0 [66] with an image size of 1280x1280px and a batchsize of 48. Unless otherwise specified, we used the provided weights pre-trained on COCO [63].…”

Section: Models and Training Setupmentioning

confidence: 99%

Leveraging Synthetic Data in Object Detection on Unmanned Aerial Vehicles

Kiefer¹,

Ott²,

Zell³

2021

Preprint

View full text Add to dashboard Cite

Acquiring data to train deep learning-based object detectors on Unmanned Aerial Vehicles (UAVs) is expensive, time-consuming and may even be prohibited by law in specific environments. On the other hand, synthetic data is fast and cheap to access. In this work, we explore the potential use of synthetic data in object detection from UAVs across various application environments. For that, we extend the open-source framework DeepGTAV to work for UAV scenarios. We capture various largescale high-resolution synthetic data sets in several domains to demonstrate their use in real-world object detection from UAVs by analyzing multiple training strategies across several models. Furthermore, we analyze several different data generation and sampling parameters to provide actionable engineering advice for further scientific research. The DeepGTAV framework is available at https://git.io/Jyf5j.

show abstract

“…From the viewpoint of early detection of events, it is sufficient to specify the region; thus, we carry out detection using a YOLO algorithm. The YOLOv5 algorithm ( Jocher et al, 2021 ) has recently been released and has been successfully used in the detection of tomato diseases ( Wang et al, 2021 ), the detection of signal lights for railways ( Liu et al, 2021 ), and the detection of smoking drivers ( Shi et al, 2021 ). All of these applications prioritize the detection speed over a reduction of the detection rate and are intended for real-time detection.…”

Section: Introductionmentioning

confidence: 99%

Early Detection of Nucleation Events From Solution in LC-TEM by Machine Learning

et al. 2022

View full text Add to dashboard Cite

To support the detection, recording, and analysis of nucleation events during in situ observations, we developed an early detection system for nucleation events observed using a liquid-cell transmission electron microscope. Detectability was achieved using the machine learning equivalent of detection by humans watching a video numerous times. The detection system was applied to the nucleation of sodium chloride crystals from a saturated acetone solution of sodium chlorate. Nanoparticles with a radius of more greater than 150 nm were detected in a viewing area of 12 μm × 12 μm by the detection system. The analysis of the change in the size of the growing particles as a function of time suggested that the crystal phase of the particles with a radius smaller than 400 nm differed from that of the crystals larger than 400 nm. Moreover, the use of machine learning enabled the detection of numerous nanometer sized nuclei. The nucleation rate estimated from the machine-learning-based detection was of the same order as that estimated from the detection using manual procedures.

show abstract

ultralytics/yolov5: v5.0 - YOLOv5-P6 1280 models, AWS, Supervise.ly and YouTube integrations

Cited by 113 publications

References 0 publications

Network-level Safety Metrics for Overall Traffic Safety Assessment: A Case Study

Network-level Safety Metrics for Overall Traffic Safety Assessment: A Case Study

Leveraging Synthetic Data in Object Detection on Unmanned Aerial Vehicles

Early Detection of Nucleation Events From Solution in LC-TEM by Machine Learning

Contact Info

Product

Resources

About