Video Smoke Research Articles

Nighttime fire smoke detection system based on machine vision

A real-time machine vision-based nighttime fire smoke detection method that can be incorporated into a surveillance system for early fire alert is proposed in this paper. Nowadays, video surveillance-based early fire smoke detection is crucial to the prevention of large fires and the protection of life and goods. However, many of the known video smoke detection methods require that minimum illumination be provided for the cameras to recognize the existence of fire smoke in a scene. To overcome the nighttime limitations of video smoke detection methods, a laser light is projected into the monitored field of view, and the returning projected light section image is analyzed in order to fire smoke. If the fire smoke appears within the monitoring zone created from the diffusing or scattering projected light path, the camera sensor receives a corresponding signal. The successive processing steps of proposed real-time algorithm are using the spectral, diffusing, and scattering characteristics of the fire smoke regions in the image sequences to register the possible smoke position in a video. Characterization of smoke is carried out by calculating accumulative deviation from the extracted feature vectors, and a classification method using a fuzzy reasoning system is applied to assign a score to the potential fire smoke candidate. Experimental results in a variety of nighttime conditions demonstrate that the proposed fire smoke detection method can successfully and reliably detect fire smoke.

A double mapping framework for extraction of shape-invariant features based on multi-scale partitions with AdaBoost for video smoke detection

Traditional methods for video smoke detection can easily achieve very low training errors but their generalization performances are not good due to arbitrary shapes of smoke, intra-class variations, occlusions and clutters. To overcome these problems, a double mapping framework is proposed to extract partition based features with AdaBoost. The first mapping is from an original image to block features. A feature vector is presented by concatenating histograms of edge orientation, edge magnitude and Local Binary Pattern (LBP) bit, and densities of edge magnitude, LBP bit, color intensity and saturation. Each component of the feature vector produces a feature image. To obtain shape-invariant features, a detection window is partitioned into a set of small blocks called a partition, and many multi-scale partitions are generated by changing block sizes and partition schemes. The sum of each feature image within each block of each partition is computed to generate block features. The second mapping is from the block features to statistical features. The statistical features of the block features, such as, mean, variance, skewness, kurtosis and Hu moments, are computed on all partitions to form a feature pool. AdaBoost is used to select discriminative shape-invariant features from the feature pool. Experiments show that the proposed method has better generalization performance and less insensitivity to geometry transform than traditional methods.

Video Fire Smoke Detection Using Motion and Color Features

A novel video smoke detection method using both color and motion features is presented. The result of optical flow is assumed to be an approximation of motion field. Background estimation and color-based decision rule are used to determine candidate smoke regions. The Lucas Kanade optical flow algorithm is proposed to calculate the optical flow of candidate regions. And the motion features are calculated from the optical flow results and use to differentiate smoke from some other moving objects. Finally, a back-propagation neural network is used to classify the smoke features from non-fire smoke features. Experiments show that the algorithm is significant for improving the accuracy of video smoke detection and reducing false alarms.

Positive impact of a shelter-based hepatitis B vaccine program in homeless Baltimore children and adolescents.

Homeless youth are at increased risk for hepatitis B virus (HBV) infection and HBV vaccine coverage is poor in this group. The purpose of our study was to determine if a shelter-based HBV vaccine program in children and adolescents 2-18 years of age with a randomized controlled trial using a culturally appropriate HBV video could increase HBV vaccine coverage rates. Subjects were randomized to an 8 min HBV video or a control, smoking prevention video. Before exposure to the videos, HBV knowledge, and demographics were assessed in caregivers and adolescents. HBV vaccine no. 1 was offered to all subjects who did not produce a vaccine record; subsequently, an accurate HBV vaccine history was obtained from medical providers. Subjects were asked to return 1 and 3 months after visit 1, HBV vaccine was offered to all with incomplete coverage, and HBV knowledge was reassessed. There were 328 children and adolescents cared for by 170 caregivers enrolled in the study. One hundred and four had incomplete HBV vaccine coverage. Data are reported for all family units with at least one subject needing vaccine. There were 53 children and adolescents randomized to the HBV video vs. 51 to the smoking video. HBV knowledge scores of caregivers improved at Visit no. 2 vs. no. 1 in the HBV video group (p = 0.01) but not in the smoking group (p = 0.82). Similar results were observed for adolescents in the HBV video group (p = 0.05) but not in the smoking group (p = 0.40). Exposure to the HBV video vs the smoking video had a significant effect on return rates for vaccine at Visit no. 2 (59 vs. 31%; p = 0.05) but not at Visit no. 3 (47 vs. 18%, p = 0.06). The shelter-based vaccine program was very effective in increasing HBV coverage rates in the entire group of 328 children and adolescents enrolled in the study, from 68% coverage at baseline to 85% at the conclusion of the study. We conclude that shelter-based HBV vaccine programs can be highly effective in increasing vaccine coverage rates in older children and adolescents. A brief exposure to a culturally appropriate HBV video improves HBV knowledge and may improve return rates for vaccine.

A fast accumulative motion orientation model based on integral image for video smoke detection

Video smoke detection has many advantages over traditional methods, such as fast response, non-contact, and so on. But most of video smoke detection systems usually have high false alarms. In order to improve the performance of video smoke detection, we propose an accumulative motion model based on the integral image by fast estimating the motion orientation of smoke. But the estimation is not very precise due to block sum. Not very accurate estimation will affect the subsequent decision. To reduce this influence, the accumulation of the orientation over time is performed to compensate results for the inaccuracy of orientation. The model is able to mostly eliminate the disturbance of artificial lights and non-smoke moving objects by using the accumulation of motion. The model together with chrominance detection can correctly detect the existence of smoke. Experimental results show that our algorithm has good robustness for smoke detection.

Cortical Stimulation of the Prefrontal Cortex With Transcranial Direct Current Stimulation Reduces Cue-Provoked Smoking Craving

Because neuroimaging studies have shown that cue-provoked smoking craving is associated with changes in the activity of the bilateral dorsolateral prefrontal cortex (DLPFC), we aimed to investigate whether a powerful technique of noninvasive brain stimulation, transcranial direct current stimulation (tDCS), reduces cue-provoked smoking craving as indexed by a visual analog scale. We performed a randomized, sham-controlled crossover study in which 24 subjects received sham and active tDCS (anodal tDCS of the left and right DLPFC) in a randomized order. Craving was induced by cigarette manipulation and exposure to a smoking video. The study ran from January 2006 to October 2006. Smoking craving was significantly increased after exposure to smoking-craving cues (p < .0001). Stimulation of both left and right DLPFC with active, but not sham, tDCS reduced craving significantly when comparing craving at baseline and after stimulation, without (p = .007) and with (p = .005) smoking-craving cues. There were no significant mood changes in any of the conditions of stimulation. Adverse events were mild and distributed equally across all treatment conditions. Our findings extend the results of a previous study on the use of brain stimulation to reduce craving, showing that cortical stimulation with tDCS is beneficial for reducing cue-provoked craving, and thus support the further exploration of this technique for smoking cessation.

Smoking-related videos for use in cue-induced craving paradigms

Environmental cues (e.g., the sight of a cigarette) have long been recognized as important triggers for craving in smokers. Available imaging technologies (e.g., fMRI) allow investigation of the neural mechanisms for cue-induced craving, but there stands a need for a cue-delivery system compatible with an MRI environment. We developed a standardized set of 24 high-resolution videos, 12 containing cigarette smoking scenes (e.g., lighting up), and 12 containing neutral scenes (e.g., reading a book), each 30 s long, with comparable lighting, visual complexity, and background filmed by a professional cinematographer. Study participants were 20 smokers (mean age = 37.7 years, 50% female). Each was exposed to the 24 videos in a random order under laboratory conditions. Dependent measures included heart rate, blood pressure, skin conductance, skin temperature, and self-reported craving (0–100) following each video. Overall findings indicated that smokers had greater reactivity to the smoking videos than to neutral videos ( p < .01). Follow-up univariate analyses revealed significant cue effects on self-reported craving, galvanic skin response, and skin temperature. Interestingly, exploratory examination of gender revealed that men had higher blood pressure and skin temperature responses than women, and that women had higher responses when viewing videos of women smoking than when viewing men smoking. Results support this set of videos as an effective tool for investigation of cue-elicited craving, and raise the possibility of unique gender effects in cue reactivity.

Effect of stage of change on cue reactivity in continuing smokers.

Three classical conditioning models (the conditioned compensatory response, conditioned withdrawal, and conditioned appetitive motivational models) postulate that drug cues evoke physiological and emotional responses associated with motivational states that prompt drug use. There is accumulating evidence to suggest that factors other than classical conditioning can influence emotional and physiological reactivity to drug stimuli. This study tested whether stage of change affects the nature of reactivity to smoking cues among continuing smokers. Precontemplators (smokers not considering quitting) and contemplators (smokers considering quitting in the near future) watched videotapes containing smoking cues. Emotional and physiological responses to the smoking video were contrasted with responses to a neutral videotape. Precontemplators had lower heart rates than did contemplators in response to the smoking videotape. Both contemplators and precontemplators evinced increased positive affect in response to the smoking cue. A comparison sample of nonsmokers did not show any reactivity to the smoking cue. Implications of these findings for conditioning theories of smoking are discussed.