A Delay Metric for Video Object Detection: What Average Precision Fails to Tell

Mao, Huizi; Yang, Xiaodong; Dally, Bill

doi:10.1109/iccv.2019.00066

Cited by 39 publications

(23 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides, densely annotated dataset can benefit for delay evaluation. Recently, average delay(AD) [45] is presented as a new metric to measure the detection delay of video object detectors. We want to know whether AD is suitable for video taken by drones, since the low resolution and wide FoV caused by long distance may hinder the delay measurement.…”

Section: Discussionmentioning

confidence: 99%

Towards Drone-Sourced Live Video Analytics via Adaptive-yet-Compatible Compression

Guo

Peng

2021

Proceedings of the 22nd International Workshop on Mobile Computing Systems and Applications

View full text Add to dashboard Cite

In this work, we present DCC (Deeper-yet-Compatible Compression), one enabling technique for real-time drone-sourced edge-assisted video analytics built on top of the existing codec. DCC tackles an important technical problem to compress streamed video from the drone to the edge without scarifying accuracy and timeliness of video analytical tasks performed at the edge. DCC is inspired by the fact that not every bit in streamed video is equally valuable to video analytics, which opens new compression room over the conventional analytics-oblivious video codec technology. We exploit drone-specific context and intermediate hints from object detection to pursue adaptive fidelity needed to retain analytical quality. We have prototyped DCC in one showcase application of vehicle detection and validated its efficiency in representative scenarios. DCC has reduced transmission volume by 9.5-fold over the baseline approach and 19-683% over [1] with comparable detection accuracy.

show abstract

Section: Discussionmentioning

confidence: 99%

Towards Drone-Sourced Live Video Analytics via Adaptive-yet-Compatible Compression

Guo

Peng

2021

Proceedings of the 22nd International Workshop on Mobile Computing Systems and Applications

View full text Add to dashboard Cite

show abstract

“…Some paper proposes the special video metrics. Mao et al propose a novel metric called Average Delay to comprehensively evaluate video object detection [188]. Delay refers to the number of frames from when an object appears to when it is detected.…”

Section: The Evaluation Methods Of Video Detectionmentioning

confidence: 99%

Visual Feature Learning on Video Object and Human Action Detection: A Systematic Review

Wang

Chen

et al. 2021

Micromachines

View full text Add to dashboard Cite

Video object and human action detection are applied in many fields, such as video surveillance, face recognition, etc. Video object detection includes object classification and object location within the frame. Human action recognition is the detection of human actions. Usually, video detection is more challenging than image detection, since video frames are often more blurry than images. Moreover, video detection often has other difficulties, such as video defocus, motion blur, part occlusion, etc. Nowadays, the video detection technology is able to implement real-time detection, or high-accurate detection of blurry video frames. In this paper, various video object and human action detection approaches are reviewed and discussed, many of them have performed state-of-the-art results. We mainly review and discuss the classic video detection methods with supervised learning. In addition, the frequently-used video object detection and human action recognition datasets are reviewed. Finally, a summarization of the video detection is represented, e.g., the video object and human action detection methods could be classified into frame-by-frame (frame-based) detection, extracting-key-frame detection and using-temporal-information detection; the methods of utilizing temporal information of adjacent video frames are mainly the optical flow method, Long Short-Term Memory and convolution among adjacent frames.

show abstract

“…It is therefore important that it not only detects with high accuracy, but with low latency, especially when dealing with moving vehicles. Other studies confirm that AP alone is not enough to evaluate object detectors, particularly when it comes to video object detection [39]. Consequently, frames per second (FPS) is another metric used to evaluate the proposed system.…”

Section: P Recision = T P T P +mentioning

confidence: 95%

Identification of Driver Phone Usage Violations via State-of-the-Art Object Detection with Tracking

Carrell¹,

Atapour-Abarghouei²

2021

Preprint

View full text Add to dashboard Cite

The use of mobiles phones when driving have been a major factor when it comes to road traffic incidents and the process of capturing such violations can be a laborious task. Advancements in both modern object detection frameworks and high-performance hardware has paved the way for a more automated approach when it comes to video surveillance. In this work, we propose a custom-trained state-of-the-art object detector to work with roadside cameras to capture driver phone usage without the need for human intervention. The proposed approach also addresses the issues caused by windscreen glare and introduces the steps required to remedy this. Twelve pretrained models are fine-tuned with our custom dataset using four popular object detection methods: YOLO, SSD, Faster R-CNN, and CenterNet. Out of all the object detectors tested, the YOLO yields the highest accuracy levels of up to ∼96% (AP10) and frame rates of up to ∼30 FPS. DeepSort object tracking algorithm is also integrated into the best-performing model to collect records of only the unique violations, and enable the proposed approach to count the number of vehicles. The proposed automated system will collect the output images of the identified violations, timestamps of each violation, and total vehicle count. Data can be accessed via a purpose-built user interface.

show abstract

A Delay Metric for Video Object Detection: What Average Precision Fails to Tell

Cited by 39 publications

References 30 publications

Towards Drone-Sourced Live Video Analytics via Adaptive-yet-Compatible Compression

Towards Drone-Sourced Live Video Analytics via Adaptive-yet-Compatible Compression

Visual Feature Learning on Video Object and Human Action Detection: A Systematic Review

Identification of Driver Phone Usage Violations via State-of-the-Art Object Detection with Tracking

Contact Info

Product

Resources

About