Cigarette smoke detection from captured image sequences

Kentaro, Iwamoto; Inoue, Hironori; Matsubara, Takamitsu; Tanaka, Toshihisa

doi:10.1117/12.840133

Cited by 6 publications

(2 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“… Wu and Chen (2011) proposed a system for smoking behavior detection through facial analysis, which accurately and rapidly discerns whether individuals in images are smoking. Iwamoto et al (2010) introduced a smoke detection method based on image sequences, utilizing convolutional neural networks (CNNs) to process continuous video frames and detect the presence of smoke. Ali et al (2012) presented an automated system named mPuff for detecting inhalations of cigarette smoke from respiratory measurements.…”

Section: Related Workmentioning

confidence: 99%

Smoking behavior detection algorithm based on YOLOv8-MNC

Wang,

Lei,

Shi

2023

Front. Comput. Neurosci.

View full text Add to dashboard Cite

IntroductionThe detection of smoking behavior is an emerging field faced with challenges in identifying small, frequently occluded objects like cigarette butts using existing deep learning technologies. Such challenges have led to unsatisfactory detection accuracy and poor model robustness.MethodsTo overcome these issues, this paper introduces a novel smoking detection algorithm, YOLOv8-MNC, which builds on the YOLOv8 network and includes a specialized layer for small target detection. The YOLOv8-MNC algorithm employs three key strategies: (1) It utilizes NWD Loss to mitigate the effects of minor deviations in object positions on IoU, thereby enhancing training accuracy; (2) It incorporates the Multi-head Self-Attention Mechanism (MHSA) to bolster the network’s global feature learning capacity; and (3) It implements the lightweight general up-sampling operator CARAFE, in place of conventional nearest-neighbor interpolation up-sampling modules, minimizing feature information loss during the up-sampling process.ResultsExperimental results from a customized smoking behavior dataset demonstrate significant improvement in detection accuracy. The YOLOv8-MNC model achieved a detection accuracy of 85.887%, signifying a remarkable increase of 5.7% in the mean Average Precision (mAP@0.5) when compared to the previous algorithm.DiscussionThe YOLOv8-MNC algorithm represents a valuable step forward in resolving existing problems in smoking behavior detection. Its enhanced performance in both detection accuracy and robustness indicates potential applicability in related fields, thus illustrating a meaningful advancement in the sphere of smoking behavior detection. Future efforts will focus on refining this technique and exploring its application in broader contexts.

show abstract

Section: Related Workmentioning

confidence: 99%

Smoking behavior detection algorithm based on YOLOv8-MNC

Wang,

Lei,

Shi

2023

Front. Comput. Neurosci.

View full text Add to dashboard Cite

show abstract

“…As in [9], the author collects the respiratory signal and hand-to-mouth gesture patterns of volunteers through a non-invasive wearable device, and then analyzed the collected data for smoking detection, this method requires high sensitivity and high cost of the sensor. The smoking detection method based on image processing [5] is to separate cigarettes and smoke from the background, and then judge according to the specific physical features such as contour, shape, color and texture. As in [8] detected smoking by analyzing the RGB spatial color features of smoke, extracting the foreground images, and analyzing the area changes and distance change of face and smoke images.…”

Section: Introductionmentioning

confidence: 99%

Real Time Detection of Drivers’ Smoking Behavior Using the Improved YOLO-V4 Model

Zhao¹

2022

Proceedings of the 2022 2nd International Conference on Computer Technology and Media Convergence Design (CTMCD 2022)

View full text Add to dashboard Cite

Drivers' smoking behavior is one of the causes of traffic accidents. The traditional sensor-based smoking detection methods are expensive. Therefore, the method based on deep learning is used for smoking detection. However, due to the limitation of GPU computing hardware, deep learning detection algorithm is difficult to deploy. To solve this problem, this paper designs an improved YOLO-V4 lightweight target detection algorithm model, namely, SmokeNet, to detect smoking behavior, which not only has high recognition accuracy, but also can meet the conditions of real-time detection on the edge devices. First, we established a smoking data set, according to the characteristics of the dataset, we reconstructed the network structure of yolov4, reduced a large number of convolution layers, and retained only one head detection layer. Then, attention mechanism is introduced to improve the model fitting ability. Finally, we deploy the trained model in Jetson Xavier NX. Experiments show that the detection accuracy of smokenet is slightly lower than that of the original yolov4 model, but the size of the model is only 1/10 of that of yolov4, and the detection speed is increased by 57%.

show abstract