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

Abstract

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.

Video smoke detection methods combining improved YUV color model and image blocks

“…At present, the camera resolution carried by most UAVs has generally reached 1080P, the amount of data in a minute is about 1.244×10 9 bits [11] Such a large amount of data is a great pressure to ensure the real-time performance of UAV smoke detection. Therefore, the idea of image block is adopted to keep the block of suspected smoke area and discard the block of smoke-free information, which can greatly reduce the amount of subsequent data processing of UAV to ensure its real-time performance.…”

Toward Bionic Arthroscopy: A Comprehensive Perspective of Continuum Robotics Principles and Prototypes for the Inception of Arthroscopic Surgery Robots

“…Rigid continuum structures refer to the mode of force and torque transmission directly through rigid elements. [59] Driven by the demand for high flexibility and small scale in medical intervention surgeries, there has been a great deal of innovation in the design of rigid continuum robots, [21,24,60] which can be classified as steerable needles, [61][62][63] concentric tubes, [64][65][66][67][68] notch tubes, [69][70][71] and backbone-based (hinged or continuous) robots. [30,[72][73][74][75] Figure 2 illustrates examples of implementations using these design principles.…”

Novel Video Surveillance-Based Fire and Smoke Classification Using Attentional Feature Map in Capsule Networks

“…Various deep learning approaches for fire detection have been proposed [ 24 ] through studies on forest fire alarms conducted using fire patches with a fine-tuned pre-released CNN, called “Alexnet” [ 25 , 26 ]. In [ 27 ], CNN-based fire detection approaches VGG-16 [ 28 ], ResNet-50 [ 29 ], and Yolo3 [ 30 ] were proposed as a reference architecture.…”