Robust Little Flame Detection on Real-Time Video Surveillance System

Lai, Tai Yu; Kuo, Jong-Yih; Fanjiang, Yong-Yi; Ma, Shang‐Pin; Liao, Yi Han

doi:10.1109/ibica.2012.41

Cited by 12 publications

(3 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In real-world scenarios, activity recognition has many use-cases and can be critical due to physical limitations and time constraints. Some examples include fire detection [18], airport security [44], smart hospitals [42,49], and elderly care [15]. Since we desired a task where users are novices and do not require any certain expertise or professional training, we chose a cooking video scenario where the system was designed to identify cooking-related tasks in a kitchen.…”

Section: Explainable Systemmentioning

confidence: 99%

Anchoring Bias Affects Mental Model Formation and User Reliance in Explainable AI Systems

Nourani

Roy²,

Block³

et al. 2021

26th International Conference on Intelligent User Interfaces

View full text Add to dashboard Cite

EXplainable Artificial Intelligence (XAI) approaches are used to bring transparency to machine learning and artificial intelligence models, and hence, improve the decision-making process for their end-users. While these methods aim to improve human understanding and their mental models, cognitive biases can still influence a user's mental model and decision-making in ways that system designers do not anticipate. This paper presents research on cognitive biases due to ordering effects in intelligent systems. We conducted a controlled user study to understand how the order of observing system weaknesses and strengths can affect the user's mental model, task performance, and reliance on the intelligent system, and we investigate the role of explanations in addressing this bias. Using an explainable video activity recognition tool in the cooking domain, we asked participants to verify whether a set of kitchen policies are being followed, with each policy focusing on a weakness or a strength. We controlled the order of the policies and the presence of explanations to test our hypotheses. Our main finding shows that those who observed system strengths early-on were more prone to automation bias and made significantly more errors due to positive first impressions of the system, while they built a more accurate mental model of the system competencies. On the other hand, those who encountered weaknesses earlier made significantly fewer errors since they tended to rely more on themselves, while they also underestimated model competencies due to having a more negative first impression of the model. Our work presents strong findings that aim to make intelligent system designers aware of such biases when designing such tools.

show abstract

Section: Explainable Systemmentioning

confidence: 99%

Anchoring Bias Affects Mental Model Formation and User Reliance in Explainable AI Systems

Nourani

Roy²,

Block³

et al. 2021

26th International Conference on Intelligent User Interfaces

View full text Add to dashboard Cite

show abstract

“…Our experiments were conducted using a custom-developed explainable activity recognition system for video. Activity recognition is an ideal test bed for XAI research due to its many potential realworld applications (e.g., fire detection [44], airport security [88], smart hospitals [77,96], and elderly care [39]) and because most activity recognition systems involve a substantial human-computer interaction component. Our goal is to study system understanding and system effectiveness among a non-specialist population, i.e., users without any particular domain expertise or AI knowledge.…”

Section: Explainable Video Activity Recognition Systemmentioning

confidence: 99%

Don't Explain without Verifying Veracity: An Evaluation of Explainable AI with Video Activity Recognition

Nourani,

Roy,

Rahman

et al. 2020

Preprint

View full text Add to dashboard Cite

Explainable machine learning and artificial intelligence models have been used to justify a model's decisionmaking process. This added transparency aims to help improve user performance and understanding of the underlying model. However, in practice, explainable systems face many open questions and challenges. Specifically, designers might reduce the complexity of deep learning models in order to provide interpretability. The explanations generated by these simplified models, however, might not accurately justify and be truthful to the model. This can further add confusion to the users as they might not find the explanations meaningful with respect to the model predictions. Understanding how these explanations affect user behavior is an ongoing challenge. In this paper, we explore how explanation veracity affects user performance and agreement in intelligent systems. Through a controlled user study with an explainable activity recognition system, we compare variations in explanation veracity for a video review and querying task. The results suggest that low veracity explanations significantly decrease user performance and agreement compared to both accurate explanations and a system without explanations. These findings demonstrate the importance of accurate and understandable explanations and caution that poor explanations can sometimes be worse than no explanations with respect to their effect on user performance and reliance on an AI system. CCS Concepts: • Human-centered computing → Empirical studies in HCI; User studies; • Computing methodologies → Machine learning approaches.

show abstract

“…As such, the color information of a pixel was usually used to determine whether the pixel belongs to a candidate flame area. The commonly used color spaces are the RGB color space [2], [3]� [6], the YCbCr color space [7], [8], the YUV color space [9], [10], the CIEL *a*b* color space [11], and the HSV color space [12]. In terms of color characteristics, the methods presented in the literature can be classified into three categories: i) Based on distribution.…”

Section: Introductionmentioning

confidence: 99%

A flame detection algorithm based on Bag-of-Features in the YUV color space

Liu

Zhang

Yang

et al. 2015

Proceedings of 2015 International Conference on Intelligent Computing and Internet of Things

View full text Add to dashboard Cite

Computer vision-based fire detection involves flame detection and smoke detection. This paper proposes a new flame detection algorithm, which is based on a Bag-of-Features technique in the YUV color space. Inspired by that the color of flame in image and video will fall in certain regions in the color space, models of flame pixels and non-flame pixels are established based on code book in the training phase in our proposal. In the testing phase, the input image is split into some NxN blocks and each block is classified respectively. In each NxN block, the pixels values in the YUV color space are extracted as features, just as in the training phase. According to the experimental results, our proposed method can reduce the number of false alarms greatly compared with an alternative algorithm, while it also ensures the accurate classification of positive samples. The classification performance of our proposed method is better than that of alternative algorithms.

show abstract

Robust Little Flame Detection on Real-Time Video Surveillance System

Cited by 12 publications

References 5 publications

Anchoring Bias Affects Mental Model Formation and User Reliance in Explainable AI Systems

Anchoring Bias Affects Mental Model Formation and User Reliance in Explainable AI Systems

Don't Explain without Verifying Veracity: An Evaluation of Explainable AI with Video Activity Recognition

A flame detection algorithm based on Bag-of-Features in the YUV color space

Contact Info

Product

Resources

About