scholarly journals Video Smoke Detection Method Based on Change-Cumulative Image and Fusion Deep Network

Sensors ◽  
2019 ◽  
Vol 19 (23) ◽  
pp. 5060
Author(s):  
Liu ◽  
Cheng ◽  
Du ◽  
Luo ◽  
Zhang ◽  
...  
Keyword(s):  
False Alarm ◽  
False Alarm Rate ◽  
Network Model ◽  
Network Models ◽  
Fire Detection ◽  
Input Image ◽  
Detection Performance ◽  
Smoke Detection ◽  
Deep Network ◽  
Better Than

Smoke detection technology based on computer vision is a popular research direction in fire detection. This technology is widely used in outdoor fire detection fields (e.g., forest fire detection). Smoke detection is often based on features such as color, shape, texture, and motion to distinguish between smoke and non-smoke objects. However, the salience and robustness of these features are insufficiently strong, resulting in low smoke detection performance under complex environment. Deep learning technology has improved smoke detection performance to a certain degree, but extracting smoke detail features is difficult when the number of network layers is small. With no effective use of smoke motion characteristics, indicators such as false alarm rate are high in video smoke detection. To enhance the detection performance of smoke objects in videos, this paper proposes a concept of change-cumulative image by converting the YUV color space of multi-frame video images into a change-cumulative image, which can represent the motion and color-change characteristics of smoke. Then, a fusion deep network is designed, which increases the depth of the VGG16 network by arranging two convolutional layers after each of its convolutional layer. The VGG16 and Resnet50 (Deep residual network) network models are also arranged using the fusion deep network to improve feature expression ability while increasing the depth of the whole network. Doing so can help extract additional discriminating characteristics of smoke. Experimental results show that by using the change-cumulative image as the input image of the deep network model, smoke detection performance is superior to the classic RGB input image; the smoke detection performance of the fusion deep network model is better than that of the single VGG16 and Resnet50 network models; the smoke detection accuracy, false positive rate, and false alarm rate of this method are better than those of the current popular methods of video smoke detection.

scholarly journals Implementation of a Modified Faster R-CNN for Target Detection Technology of Coastal Defense Radar

2021 ◽  
Vol 13 (9) ◽  
pp. 1703
Author(s):  
He Yan ◽  
Chao Chen ◽  
Guodong Jin ◽  
Jindong Zhang ◽  
Xudong Wang ◽  
...  
Keyword(s):  
False Alarm ◽  
False Alarm Rate ◽  
Target Detection ◽  
Real Data ◽  
Detection Performance ◽  
Detection Accuracy ◽  
Constant False Alarm Rate ◽  
Data Set ◽  
Detection Technology ◽  
Coastal Defense

The traditional method of constant false-alarm rate detection is based on the assumption of an echo statistical model. The target recognition accuracy rate and the high false-alarm rate under the background of sea clutter and other interferences are very low. Therefore, computer vision technology is widely discussed to improve the detection performance. However, the majority of studies have focused on the synthetic aperture radar because of its high resolution. For the defense radar, the detection performance is not satisfactory because of its low resolution. To this end, we herein propose a novel target detection method for the coastal defense radar based on faster region-based convolutional neural network (Faster R-CNN). The main processing steps are as follows: (1) the Faster R-CNN is selected as the sea-surface target detector because of its high target detection accuracy; (2) a modified Faster R-CNN based on the characteristics of sparsity and small target size in the data set is employed; and (3) soft non-maximum suppression is exploited to eliminate the possible overlapped detection boxes. Furthermore, detailed comparative experiments based on a real data set of coastal defense radar are performed. The mean average precision of the proposed method is improved by 10.86% compared with that of the original Faster R-CNN.

Can Network Models Represent Personality Structure and Processes Better than Trait Models Do?

2012 ◽  
Vol 26 (4) ◽  
pp. 444-445 ◽  
Author(s):  
Tobias Rothmund ◽  
Anna Baumert ◽  
Manfred Schmitt
Keyword(s):  
Network Model ◽  
Explanatory Power ◽  
Network Models ◽  
Personality Structure ◽  
Psychological Processes ◽  
Target Article ◽  
Flexible Framework ◽  
Trait Model ◽  
Better Than

We argue that replacing the trait model with the network model proposed in the target article would be immature for three reasons. (i) If properly specified and grounded in substantive theories, the classic state–trait model provides a flexible framework for the description and explanation of person × situation transactions. (ii) Without additional substantive theories, the network model cannot guide the identification of personality components. (iii) Without assumptions about psychological processes that account for causal links among personality components, the concept of equilibrium has merely descriptive value and lacks explanatory power. Copyright © 2012 John Wiley & Sons, Ltd.

scholarly journals LA-GRU: Building Combined Intrusion Detection Model Based on Imbalanced Learning and Gated Recurrent Unit Neural Network

2018 ◽  
Vol 2018 ◽  
pp. 1-13 ◽  
Author(s):  
Binghao Yan ◽  
Guodong Han
Keyword(s):  
Neural Network ◽  
Intrusion Detection ◽  
False Alarm ◽  
False Alarm Rate ◽  
Network Traffic ◽  
Detection Performance ◽  
Imbalanced Learning ◽  
Traffic Distribution ◽  
Proposed Model ◽  
Gated Recurrent Unit

The intrusion detection models (IDMs) based on machine learning play a vital role in the security protection of the network environment, and, by learning the characteristics of the network traffic, these IDMs can divide the network traffic into normal behavior or attack behavior automatically. However, existing IDMs cannot solve the imbalance of traffic distribution, while ignoring the temporal relationship within traffic, which result in the reduction of the detection performance of the IDM and increase the false alarm rate, especially for low-frequency attacks. So, in this paper, we propose a new combined IDM called LA-GRU based on a novel imbalanced learning method and gated recurrent unit (GRU) neural network. In the proposed model, a modified local adaptive synthetic minority oversampling technique (LA-SMOTE) algorithm is provided to handle imbalanced traffic, and then the GRU neural network based on deep learning theory is used to implement the anomaly detection of traffic. The experimental results evaluated on the NSL-KDD dataset confirm that, compared with the existing state-of-the-art IDMs, the proposed model not only obtains excellent overall detection performance with a low false alarm rate but also more effectively solves the learning problem of imbalanced traffic distribution.

A Novel Network Traffic Anomaly Detection Based on Multi-Scale Fusion

2011 ◽  
Vol 48-49 ◽  
pp. 102-105
Author(s):  
Guo Zhen Cheng ◽  
Dong Nian Cheng ◽  
He Lei
Keyword(s):  
Anomaly Detection ◽  
False Alarm ◽  
False Alarm Rate ◽  
Network Traffic ◽  
Self Similarity ◽  
Data Set ◽  
Multi Scale ◽  
Traffic Anomaly ◽  
Detection Evaluation ◽  
Better Than

Detecting network traffic anomaly is very important for network security. But it has high false alarm rate, low detect rate and that can’t perform real-time detection in the backbone very well due to its nonlinearity, nonstationarity and self-similarity. Therefore we propose a novel detection method—EMD-DS, and prove that it can reduce mean error rate of anomaly detection efficiently after EMD. On the KDD CUP 1999 intrusion detection evaluation data set, this detector detects 85.1% attacks at low false alarm rate which is better than some other systems.

scholarly journals Fire detection with infrared images using cascaded neural network

2019 ◽  
Vol 13 ◽  
pp. 174830261989543
Author(s):  
Li Deng ◽  
Qian Chen ◽  
Yuanhua He ◽  
Xiubao Sui ◽  
Quanyi Liu ◽  
...  
Keyword(s):  
Neural Network ◽  
False Alarm ◽  
False Alarm Rate ◽  
Early Stage ◽  
Infrared Camera ◽  
Fire Detection ◽  
Image Texture ◽  
Infrared Images ◽  
Detection Technology ◽  
Civil Aircraft

The existing equipment of civil aircraft cargo fire detection mainly uses photoelectric smoke detectors, which has a high false alarm rate. According to Federal Aviation Agency’s (FAA) statistics, the false alarm rate is as high as 99%. 1 In the cargo of civil aircraft, the traditional photoelectric detection technology cannot effectively distinguish interference particles from smoke particles. Since the video smoke detection technology has proven to be reliable in many large scenarios, a deep learning method of image processing for fire detection is proposed. The proposed convolutional neural network is constructed of front end network and back end network cascaded with the capsule network and the circularity computation for the dynamic infrared fire image texture extraction. In order to accurately identify whether there is a fire in the area and give the kind of burning substances, a series of fuels are selected, such as n-heptane, cyclohexane, and carton for combustion reaction, and infrared camera is used to take infrared images of all fuel combustion. Experimental results show that the proposed method can effectively detect fire at the early stage of fire which is applicable for fire detection in civil aircraft cargoes.

scholarly journals Adjacent Infrared Multitarget Detection Using Robust Background Estimation

2016 ◽  
Vol 2016 ◽  
pp. 1-10 ◽  
Author(s):  
Sungho Kim ◽  
Kyung-Tae Kim
Keyword(s):  
False Alarm ◽  
False Alarm Rate ◽  
Target Detection ◽  
Detection Method ◽  
Detection Performance ◽  
Detection Methods ◽  
Constant False Alarm Rate ◽  
Cluttered Environments ◽  
Background Estimation ◽  
Cfar Detection

Small target detection is very important for infrared search and track (IRST) problems. Grouped targets are difficult to detect using the conventional constant false alarm rate (CFAR) detection method. In this study, a novel multitarget detection method was developed to identify adjacent or closely spaced small infrared targets. The neighboring targets decrease the signal-to-clutter ratio in hysteresis threshold-based constant false alarm rate (H-CFAR) detection, which leads to poor detection performance in cluttered environments. The proposed adjacent target rejection-based robust background estimation can reduce the effects of the neighboring targets and enhance the small multitarget detection performance in infrared images by increasing the signal-to-clutter ratio. The experimental results of the synthetic and real adjacent target sequences showed that the proposed method produces an upgraded detection rate with the same false alarm rate compared to the recent target detection methods (H-CFAR, Top-hat, and TDLMS).

Intelligent Algorithm in Automatic Fire Alarm Application

2012 ◽  
Vol 605-607 ◽  
pp. 1851-1854
Author(s):  
Yan Qiu Wang ◽  
Yan Wen Wang ◽  
Chun Mei Pei ◽  
Xiu Qing Yang ◽  
Hai Rong Ye
Keyword(s):  
False Alarm ◽  
False Alarm Rate ◽  
Digital Filter ◽  
Fire Detection ◽  
Intelligent Algorithm ◽  
Fire Alarm ◽  
Rate Analysis ◽  
Practical Engineering ◽  
In Fire ◽  
Detection Signal

Characteristics of fire detection signal are proposed that, in fire case non-fire signals caused by other factors can not be separated from fire signals and in non-fire case non-fire signals may produce changes similar to fire signals. An intelligent algorithm is pointed out to reduce false alarm rate and miss alarm rate, it can improve fire alarm accuracy. The intelligent algorithm includes digital filter, sensitivity autoregulation, drift aotocompensation and rising rate analysis, and it is useful in practical engineering.

Optimization of deep network models through fine tuning

2018 ◽  
Vol 11 (3) ◽  
pp. 386-403 ◽  
Author(s):  
M. Arif Wani ◽  
Saduf Afzal
Keyword(s):  
Experimental Study ◽  
Deep Learning ◽  
Network Model ◽  
Network Models ◽  
Fine Tuning ◽  
Data Sets ◽  
Content Type ◽  
Deep Network ◽  
Benchmark Data ◽  
Deep Learning Model

Purpose Many strategies have been put forward for training deep network models, however, stacking of several layers of non-linearities typically results in poor propagation of gradients and activations. The purpose of this paper is to explore the use of two steps strategy where initial deep learning model is obtained first by unsupervised learning and then optimizing the initial deep learning model by fine tuning. A number of fine tuning algorithms are explored in this work for optimizing deep learning models. This includes proposing a new algorithm where Backpropagation with adaptive gain algorithm is integrated with Dropout technique and the authors evaluate its performance in the fine tuning of the pretrained deep network. Design/methodology/approach The parameters of deep neural networks are first learnt using greedy layer-wise unsupervised pretraining. The proposed technique is then used to perform supervised fine tuning of the deep neural network model. Extensive experimental study is performed to evaluate the performance of the proposed fine tuning technique on three benchmark data sets: USPS, Gisette and MNIST. The authors have tested the approach on varying size data sets which include randomly chosen training samples of size 20, 50, 70 and 100 percent from the original data set. Findings Through extensive experimental study, it is concluded that the two steps strategy and the proposed fine tuning technique significantly yield promising results in optimization of deep network models. Originality/value This paper proposes employing several algorithms for fine tuning of deep network model. A new approach that integrates adaptive gain Backpropagation (BP) algorithm with Dropout technique is proposed for fine tuning of deep networks. Evaluation and comparison of various algorithms proposed for fine tuning on three benchmark data sets is presented in the paper.

scholarly journals Smoke Image Segmentation Based on Color Model

2015 ◽  
Vol 6 (2) ◽  
pp. 130 ◽  
Author(s):  
Deng Xing ◽  
Yu Zhongming ◽  
Wang Lin ◽  
Li Jinlan
Keyword(s):  
Image Segmentation ◽  
False Alarm ◽  
False Alarm Rate ◽  
Color Space ◽  
Significant Feature ◽  
Color Model ◽  
Smoke Detection ◽  
Image Detection ◽  
Hsv Color Space ◽  
Lab Color Space

Smoke is the most significant feature in the process of fire, so it’s possible to rely on smoke detection to detect fire. While the smoke image segmentation is the most difficult and also indispensable step in the analysis of smoke image detection. In order to improve its accuracy and effectively exclude the disturbances of non-smoke image, and lower the false alarm rate, it puts forward a kind of smoke image segmentation based on color model. It uses K-means clustering in Lab color space and threshold segmentation in HSV color space, then merges the two results. Finally, it uses the method of shen filter and regional mark to denoise, Experimental results on segmentation of smoke image show that the proposed method is able to segment smoke from the background.

scholarly journals Effective Smoke Detection Using Spatial-Temporal Energy and Weber Local Descriptors in Three Orthogonal Planes (WLD-TOP)

2018 ◽  
Vol 18 (01) ◽  
pp. e05 ◽  
Author(s):  
John Adedapo Ojo ◽  
Jamiu Alabi Oladosu
Keyword(s):  
False Alarm ◽  
False Alarm Rate ◽  
Detection Rate ◽  
Robot Vision ◽  
Fire Detection ◽  
Support Vector ◽  
False Alarms ◽  
High Detection Rate ◽  
Local Descriptor ◽  
Video Frames

Video-based fire detection (VFD) technologies have received significant attention from both academic and industrial communities recently. However, existing VFD approaches are still susceptible to false alarms due to changes in illumination, camera noise, variability of shape, motion, colour, irregular patterns of smoke and flames, modelling and training inaccuracies. Hence, this work aimed at developing a VSD system that will have a high detection rate, low false-alarm rate and short response time. Moving blocks in video frames were segmented and analysed in HSI colour space, and wavelet energy analysis of the smoke candidate blocks was performed. In addition, Dynamic texture descriptors were obtained using Weber Local Descriptor in Three Orthogonal Planes (WLD-TOP). These features were combined and used as inputs to Support Vector Classifier with radial based kernel function, while post-processing stage employs temporal image filtering to reduce false alarm. The algorithm was implemented in MATLAB 8.1.0.604 (R2013a). Accuracy of 99.30%, detection rate of 99.28% and false alarm rate of 0.65% were obtained when tested with some online videos. The output of this work would find applications in early fire detection systems and other applications such as robot vision and automated inspection.

Sign in / Sign up

Export Citation Format

Share Document