scispace - formally typeset
Search or ask a question
Author

Jian Zhang

Bio: Jian Zhang is an academic researcher. The author has contributed to research in topics: Deep learning & Soft computing. The author has an hindex of 2, co-authored 2 publications receiving 52 citations.

Papers
More filters
Proceedings ArticleDOI
01 Dec 2016
TL;DR: A new approach based on deep convolutional neural networks is proposed which can be trained end to end from raw pixel values to classifier outputs and automatically extract features from images to improve smoke detection accuracy.
Abstract: An effective smoke detection from visual scenes is crucial to avoid large scale fire around the world. But it is still challenging due to its large variations in color, texture and shapes. To improve smoke detection accuracy, a new approach based on deep convolutional neural networks is proposed which can be trained end to end from raw pixel values to classifier outputs and automatically extract features from images. Experiments show that this method achieves 99.4% detection rates with 0.44% false alarm rates on the large dataset which obviously outperforms existing traditional methods.

78 citations

Proceedings ArticleDOI
01 Dec 2016
TL;DR: This review not only reveals a promising direction for soft computing by incorporating deep learning, but also gives some suggestions for improving the performance of deep learning with soft computing techniques.
Abstract: A review of deep learning based soft computing techniques in several applications is presented. On one hand, soft computing, defined as a group of methodologies, is an important element for constructing a new generation of computational intelligent system and has gained great success in solving practical computing problems. On the other hand, deep learning has become one of the most promising techniques in artificial intelligence in the past decade. Since soft computing is an evolving collection of methodologies, by presenting the latest research results of soft computing based on deep learning, this review not only reveals a promising direction for soft computing by incorporating deep learning, but also gives some suggestions for improving the performance of deep learning with soft computing techniques.

14 citations


Cited by
More filters
Journal ArticleDOI
TL;DR: A comparison of the proposed and current algorithms reveals that the accuracy of fire detection algorithms based on object detection CNNs is higher than other algorithms, and the YOLO v3 algorithm has stronger robustness of detection performance, and its detection speed reaches 28 FPS, thereby satisfying the requirements of real-time detection.

171 citations

Book ChapterDOI
25 Aug 2017
TL;DR: It turns out that a traditional CNN performs relatively poorly when evaluated on the more realistically balanced benchmark dataset provided in this paper, so it is proposed to use even deeper Convolutional Neural Networks for fire detection in images, and enhancing these with fine tuning based on a fully connected layer.
Abstract: Detecting fire in images using image processing and computer vision techniques has gained a lot of attention from researchers during the past few years. Indeed, with sufficient accuracy, such systems may outperform traditional fire detection equipment. One of the most promising techniques used in this area is Convolutional Neural Networks (CNNs). However, the previous research on fire detection with CNNs has only been evaluated on balanced datasets, which may give misleading information on real-world performance, where fire is a rare event. Actually, as demonstrated in this paper, it turns out that a traditional CNN performs relatively poorly when evaluated on the more realistically balanced benchmark dataset provided in this paper. We therefore propose to use even deeper Convolutional Neural Networks for fire detection in images, and enhancing these with fine tuning based on a fully connected layer. We use two pretrained state-of-the-art Deep CNNs, VGG16 and Resnet50, to develop our fire detection system. The Deep CNNs are tested on our imbalanced dataset, which we have assembled to replicate real world scenarios. It includes images that are particularly difficult to classify and that are deliberately unbalanced by including significantly more non-fire images than fire images. The dataset has been made available online. Our results show that adding fully connected layers for fine tuning indeed does increase accuracy, however, this also increases training time. Overall, we found that our deeper CNNs give good performance on a more challenging dataset, with Resnet50 slightly outperforming VGG16. These results may thus lead to more successful fire detection systems in practice.

126 citations

Journal ArticleDOI
TL;DR: This review is focused on video flame and smoke based fire detection algorithms for both indoor and outdoor environments and the latest trend in literature which focuses on the hybrid approach utilizing both handcraft feature, and deep learning approaches is discussed.
Abstract: This review is focused on video flame and smoke based fire detection algorithms for both indoor and outdoor environments. It analyzes and discusses them in a taxonomical manner for the last two decades. These are mainly based on handcraft features with or without classifiers and deep learning approaches. The separate treatment is provided for detecting flames and smoke. Their static and dynamic characteristics are elaborated for the handcraft feature approach. The blending of the obtained features from these characteristics is the focus of most of the research and these concepts are analyzed critically. A fusion of both visible and thermal images leading to multi-fusion and multimodal approaches have conversed. It is a step towards obtaining accurate detection results and how the handcraft feature approach tackles the problems of flame and smoke detection, as well as their weaknesses are discussed which are still not solved. Some of these weaknesses can be tackled by developing a technology based on artificial intelligence named deep-learning. Its taxonomical literature study with a focus on the flame and smoke detection is presented. The strengths and weaknesses of this approach are discussed with possible solutions. The latest trend in literature which focuses on the hybrid approach utilizing both handcraft feature, and deep learning approaches is discussed. This approach aims to minimize the weaknesses still present in the current systems.

100 citations

Journal ArticleDOI
TL;DR: A smoke detection algorithm based on the motion characteristics of smoke and the convolutional neural networks and the strategy of implicit enlarging the suspected regions is proposed, which improves the timeliness of smoke detection.
Abstract: It is a challenging task to recognize smoke from visual scenes due to large variations in the feature of color, texture, shapes, etc. The current detection algorithms are mainly based on single feature or fusion of multiple static features of smoke, which leads to low detection accuracy. To solve this problem, this paper proposes a smoke detection algorithm based on the motion characteristics of smoke and the convolutional neural networks (CNN). Firstly, a moving object detection algorithm based on background dynamic update and dark channel priori is proposed to detect the suspected smoke regions. Then, the features of suspected region is extracted automatically by CNN, on that the smoke identification is performed. Compared to previous work, our algorithm improves the detection accuracy, which can reach 99% in the testing sets. For the problem that the region of smoke is relatively small in the early stage of smoke generation, the strategy of implicit enlarging the suspected regions is proposed, which improves the timeliness of smoke detection. In addition a fine-tuning method is proposed to solve the problem of scarce of data in the training network. Also, the algorithm has good smoke detection performance by testing under various video scenes.

93 citations

Journal ArticleDOI
30 Jul 2019
TL;DR: The applications, algorithms, and solutions that have been proposed recently to facilitate edge video analytics for public safety, including the AI-dominated video analytics, are reviewed.
Abstract: With the installation of enormous public safety and transportation infrastructure cameras, video analytics has come to play an essential part in public safety. Typically, video analytics is to collectively leverage the advanced computer vision (CV) and artificial intelligence (AI) to solve the four-W problem. That is to identify Who has done something (What) at a specific place (Where) at some time (When). According to the difference of latency requirements, video analytics can be applied to postevent retrospective analysis, such as archive management, search, forensic investigation and real-time live video stream analysis, such as situation awareness, alerting, and interested object (criminal suspect/missing vehicle) detection. The latter is characterized as having higher requirements on hardware resources as the sophisticated image processing algorithms under the hood. However, analyzing large-scale live video streams on the Cloud is impractical as the edge solution that conducts the video analytics on (or close to) the camera provides a silvering light. Analyzing live video streams on the edge is not trivial due to the constrained hardware resources on edge. The AI-dominated video analytics requires higher bandwidth, consumes considerable CPU/GPU resources for processing, and demands larger memory for caching. In this paper, we review the applications, algorithms, and solutions that have been proposed recently to facilitate edge video analytics for public safety.

87 citations