Fire detection using stereoscopic imaging and image processing techniques

Li, Guodong; Lü, Gang; Yan, Yong

doi:10.1109/ist.2014.6958440

Cited by 5 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[2]. Video processing is the part of computer vision and today it is also in demand for the content based video processing such as object tracking anomaly detection, fire and smoke detection systems [3]- [4]. For the surveillance purpose, application of fire and smoke detection as tool has increase to due to the frequent occurrence of extended fire with consequences on human health and security but for the detection of fire and smoke generally electronics sensors are used [5].…”

Section: Introductionmentioning

confidence: 99%

An Optimized Surf-Based Fire and Smoke Detection System Using Image Processing From Surveillance Video.

2020

IJESRT

View full text Add to dashboard Cite

Over the last decades, digital image processing based fire and smoke detection have been improving steadily to provide a more accurate detection results in the area of surveillance security system. Detection of the fire and smoke from the surveillance videos is very challenging task due to the complex structural properties of the video frames or images and need improvisation in the existing work by utilization of feature selection or optimization approach to select on optimal feature according to the fire and smoke. A research based on the combination of various feature extraction techniques with feature selection approach for fire and smoke detection has been presented in this paper. In this research, we develop Fire and Smoke Detection (FSD) system using digital image processing with the concept of Speed up Robust Feature (SURF) along with the Intelligent Water Drops (IWD) as a feature selection and optimization algorithm. Here, Artificial Neural Network (ANN) is used as an Artificial Intelligence (AI) technique with that helps to select a set of optimal feature from the extracted by SURF descriptor from the video frames. By utilizing the concept of optimized ANN, the accuracy of proposed FSD system is increases in terms of detection accuracy and with minimum percentage of error. At last, the performance of the FSD system is calculated to validate the model and this shows that it is possible to use IWD with SURF as a feature extraction technique in order to detect the fire or smoke form the surveillance video with minimum error rate and the simulation results clearly show the effectiveness of proposed FSD system

show abstract

Section: Introductionmentioning

confidence: 99%

An Optimized Surf-Based Fire and Smoke Detection System Using Image Processing From Surveillance Video.

2020

IJESRT

View full text Add to dashboard Cite

show abstract

“…Among them, color is considered as one of the most important clues. Li et al [3] developed computer algorithms to segment the fire zone in the HSV (hue, saturation, value) color space and discover the correspondence points of image pairs, deciding the location, size, and propagation of the fire. A method based on the RGB (red, green, blue) color model and the difference between two consecutive potential fire masks was proposed in Reference [4], which indicated whether the potential region was a fire or fire-like object.…”

Section: Introductionmentioning

confidence: 99%

A Fire Detection Algorithm Based on Tchebichef Moment Invariants and PSO-SVM

et al. 2018

View full text Add to dashboard Cite

Automatic fire detection, which can detect and raise the alarm for fire early, is expected to help reduce the loss of life and property as much as possible. Due to its advantages over traditional methods, image processing technology has been applied gradually in fire detection. In this paper, a novel algorithm is proposed to achieve fire image detection, combined with Tchebichef (sometimes referred to as Chebyshev) moment invariants (TMIs) and particle swarm optimization-support vector machine (PSO-SVM). According to the correlation between geometric moments and Tchebichef moments, the translation, rotation, and scaling (TRS) invariants of Tchebichef moments are obtained first. Then, the TMIs of candidate images are calculated to construct feature vectors. To gain the best detection performance, a PSO-SVM model is proposed, where the kernel parameter and penalty factor of support vector machine (SVM) are optimized by particle swarm optimization (PSO). Then, the PSO-SVM model is utilized to identify the fire images. Compared with algorithms based on Hu moment invariants (HMIs) and Zernike moment invariants (ZMIs), the experimental results show that the proposed algorithm can improve the detection accuracy, achieving the highest detection rate of 98.18%. Moreover, it still exhibits the best performance even if the size of the training sample set is small and the images are transformed by TRS.

show abstract

“…Based on binocular stereo vision technology in fire detection and positioning has attracted much attention recently. Li, Lu and Yan proposed a stereoscopic imaging technique by A low-cost binocular CCD camera for fire detection [21]. Utilizing two or more cameras to form stereo vision can achieve a 3D reconstruction of a fire and locate a fire accurately [22,23].…”

Section: Introductionmentioning

confidence: 99%

Firefighting robot with video full-closed loop control

Wu¹,

Li²,

Ye³

et al. 2016

Int. J. SAFE

View full text Add to dashboard Cite

In view of the many problems in firefighting robots, such as complicated flame positioning, poor environmental adaptability, and difficult installation and debugging, a new firefighting robot design is presented with video full closed-loop feedback to extinguish ground fire in this paper. The firefighting robot consists of a 2-DOF robot, a monocular camera, and a controller. The monocular camera installed on the second link of the robot is utilized to detect and locate ground flames. The robot can dynamically adjust the water landing point to track a flame in real-time through motion control, as the camera is specifically designed with an additional infrared narrowband pass filter and a filter-switching mechanism. An algorithm of detecting and positioning for flame and water landing point is proposed based on image processing and robotic kinematics. Experimental results show that the firefighting robot with video full closed-loop feedback can realize real-time flame detection, location, and sprinkler, and can dynamically track fire location within the monitoring scope. The distance error between fire and the landing point of the water jet can be controlled within a narrow range. Moreover, this firefighting robot is easy to install, debug and have good environment adaptability, and provides efficient and safe solutions for complicated firefighting environment. At the same time, due to its small size and convenient calibration features, this firefighting robot is especially suitable for large space environments.

show abstract

Fire detection using stereoscopic imaging and image processing techniques

Cited by 5 publications

References 14 publications

An Optimized Surf-Based Fire and Smoke Detection System Using Image Processing From Surveillance Video.

An Optimized Surf-Based Fire and Smoke Detection System Using Image Processing From Surveillance Video.

A Fire Detection Algorithm Based on Tchebichef Moment Invariants and PSO-SVM

Firefighting robot with video full-closed loop control

Contact Info

Product

Resources

About