A Dual Convolution Network Using Dark Channel Prior for Image Smoke Classification

Liu, Yanbei; Qin, Wen; Liu, Kaihua; Zhang, Fang; Xiao, Zhitao

doi:10.1109/access.2019.2915599

Cited by 26 publications

(12 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [16], researchers demonstrated the effectiveness of saliency detection method and CNN in localization and recognition of wildfire in aerial images. Liu et al [17] proposed a dual convolution network using dark channel prior (DarkC-DCN) to further improve the recognition accuracy of image-based CNN model. To ease the limitations of smoke image samples, an end-to-end trainable framework based on fast detector SSD and MSCNN for smoke detection is proposed, which can optimize the model from synthetic and real smoke samples.…”

Section: Deep Learning Methodsmentioning

confidence: 99%

An Attention Enhanced Bidirectional LSTM for Early Forest Fire Smoke Recognition

Cao

Yang

Tang³

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Detecting forest fire smoke during the initial stages is vital for preventing forest fire events. Recent studies have shown that exploring spatial and temporal features of the image sequence is important for this task. Nevertheless, since the long distance wildfire smoke usually move slowly and lacks salient features, accurate smoke detection is still a challenging task. In this paper, we propose a novel Attention Enhanced Bidirectional Long Short-Term Memory Network (ABi-LSTM) for video based forest fire smoke recognition. The proposed ABi-LSTM consists of the spatial features extraction network, the Bidirectional Long Short-Term Memory Network(LSTM), and the temporal attention subnetwork, which can not only capture discriminative spatiotemporal features from image patch sequences but also pay different levels of attention to different patches. Experiments show that out ABi-LSTM is capable of achieving best accuracy and less false alarms on different types of scenarios. The ABi-LSTM model achieve a highly accuracy of 97.8%, and there is 4.4% improvement over the image-based deep learning model.

show abstract

Section: Deep Learning Methodsmentioning

confidence: 99%

An Attention Enhanced Bidirectional LSTM for Early Forest Fire Smoke Recognition

Cao

Yang

Tang³

et al. 2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Hu and Lu trained spatial-temporal ConvNets (similar to the two-steam model in action recognition [49]) and applied multi-task learning to avoid computing optical flow for real-time detection [24]. Liu (trained with Dark Channel images [18]) for classifying smoke [38].…”

Section: Related Workmentioning

confidence: 99%

“…1 Compared to datasets for object and action recognition, such as ImageNet [45] and Kinetics [29], existing datasets for smoke recognition are relatively small. Despite several successes in the prior works of using deep learning for smoke detection [5,15,24,33,38,[55][56][57][58][59][60]63], these models were trained and evaluated on relative small video or image datasets (Table 1). In response to data sparsity, some prior works attempted to generate artificial smoke images, where smoke emissions with transparent background were synthesized with various scenes [55,61,63].…”

Section: Introductionmentioning

confidence: 99%

Project RISE: Recognizing Industrial Smoke Emissions

Hsu¹,

Huang²,

Hu³

et al. 2020

Preprint

View full text Add to dashboard Cite

Industrial smoke emissions pose a significant concern to human health. Prior works have shown that using Computer Vision (CV) techniques to identify smoke as visual evidence can influence the attitude of regulators and empower citizens in pursuing environmental justice. However, existing datasets do not have sufficient quality nor quantity for training robust CV models to support air quality advocacy. We introduce RISE, the first large-scale video dataset for Recognizing Industrial Smoke Emissions. We adopt the citizen science approach to collaborate with local community members in annotating whether a video clip has smoke emissions. Our dataset contains 12,567 clips with 19 distinct views from cameras on three sites that monitored three different industrial facilities. The clips are from 30 days that spans four seasons in two years in the daytime. We run experiments using deep neural networks developed for video action recognition to establish a performance baseline and reveal the challenges for smoke recognition. Our data analysis also shows opportunities for integrating citizen scientists and crowd workers into the application of Artificial Intelligence for social good.

show abstract

“…The purpose of motion image deblurring is to reconstruct and estimate an unknown clear image for a motion blurred image. Traditional motion image deblurring methods estimate the parameters and model of the blur kernel, and use different natural priors in the optimization of the objective function, such as dark channel priors [1], data-driven priors [2] etc., to improve the accuracy of parameter estimation and deblurring quality. However, traditional methods are limited by fuzzy kernel estimation and inaccurate modeling of fuzzy sources, resulting in poor image reconstruction quality.…”

Section: Introductionmentioning

confidence: 99%

Generative Adversarial Network Based on Multi-feature Fusion Strategy for Motion Image Deblurring

Jin¹,

Jin²

2022

Journal of Compurters

View full text Add to dashboard Cite

<p>Deblurring of motion images is a part of the field of image restoration. The deblurring of motion images is not only difficult to estimate the motion parameters, but also contains complex factors such as noise, which makes the deblurring algorithm more difficult. Image deblurring can be divided into two categories: one is the non-blind image deblurring with known fuzzy kernel, and the other is the blind image deblurring with unknown fuzzy kernel. The traditional motion image deblurring networks ignore the non-uniformity of motion blurred images and cannot effectively recover the high frequency details and remove artifacts. In this paper, we propose a new generative adversarial network based on multi-feature fusion strategy for motion image deblurring. An adaptive residual module composed of deformation convolution module and channel attention module is constructed in the generative network. Where, the deformation convolution module learns the shape variables of motion blurred image features, and can dynamically adjust the shape and size of the convolution kernel according to the deformation information of the image, thus improving the ability of the network to adapt to image deformation. The channel attention module adjusts the extracted deformation features to obtain more high-frequency features and enhance the texture details of the restored image. Experimental results on public available GOPRO dataset show that the proposed algorithm improves the peak signal-to-noise ratio (PSNR) and is able to reconstruct high quality images with rich texture details compared to other motion image deblurring methods.</p> <p> </p>

show abstract

A Dual Convolution Network Using Dark Channel Prior for Image Smoke Classification

Cited by 26 publications

References 24 publications

An Attention Enhanced Bidirectional LSTM for Early Forest Fire Smoke Recognition

An Attention Enhanced Bidirectional LSTM for Early Forest Fire Smoke Recognition

Project RISE: Recognizing Industrial Smoke Emissions

Generative Adversarial Network Based on Multi-feature Fusion Strategy for Motion Image Deblurring

Contact Info

Product

Resources

About