Saliency Detection and Deep Learning-Based Wildfire Identification in UAV Imagery

Abstract

An unmanned aerial vehicle (UAV) equipped with global positioning systems (GPS) can provide direct georeferenced imagery, mapping an area with high resolution. So far, the major difficulty in wildfire image classification is the lack of unified identification marks, the fire features of color, shape, texture (smoke, flame, or both) and background can vary significantly from one scene to another. Deep learning (e.g., DCNN for Deep Convolutional Neural Network) is very effective in high-level feature learning, however, a substantial amount of training images dataset is obligatory in optimizing its weights value and coefficients. In this work, we proposed a new saliency detection algorithm for fast location and segmentation of core fire area in aerial images. As the proposed method can effectively avoid feature loss caused by direct resizing; it is used in data augmentation and formation of a standard fire image dataset ‘UAV_Fire’. A 15-layered self-learning DCNN architecture named ‘Fire_Net’ is then presented as a self-learning fire feature exactor and classifier. We evaluated different architectures and several key parameters (drop out ratio, batch size, etc.) of the DCNN model regarding its validation accuracy. The proposed architecture outperformed previous methods by achieving an overall accuracy of 98%. Furthermore, ‘Fire_Net’ guarantied an average processing speed of 41.5 ms per image for real-time wildfire inspection. To demonstrate its practical utility, Fire_Net is tested on 40 sampled images in wildfire news reports and all of them have been accurately identified.

A Review on IoT Deep Learning UAV Systems for Autonomous Obstacle Detection and Collision Avoidance

“…For instance, in the work by the authors of [39], the current literature is systematically reviewed according to a taxonomy that includes different abstraction levels related to perception, guidance, navigation, and control. Other authors focused only on solving specific problems (e.g., counting cars in UAV images [40]) or on improving specific algorithms [41,42]. Nevertheless, most of the current literature cannot be considered IoT-enabled, and, to the best of our knowledge, there are no articles that review the whole DL-UAV architecture while focusing on the problem of autonomous obstacle detection and collision avoidance.…”

Deep-Learning-Based Aerial Image Classification for Emergency Response Applications Using Unmanned Aerial Vehicles

“…The work in [27] proposes an approach comprised of a convolutional neural network called Fire_Net consisting of 15 layers with an architecture similar to the VGG16 network with 8 convolutional, 4 max-pooling, and 2 fully connected layers for recognizing fire in 128 × 128 resolution images. It is accompanied by a region proposal algorithm that extracts image regions from larger resolution images so that they can be classified by the neural network.…”

Estimating Departure Time Using Thermal Camera and Heat Traces Tracking Technique

“…Far-infrared thermal imaging has been widely used in respiratory monitoring in telemedicine [10,11], obstacle detection [12,13] and pedestrian detection [14,15] in smart traffic, fault detection in smart industry [16,17], fire safety in smart cities [18,19], body temperature detection of pig in agriculture [20], etc. In criminal investigation, Pavlidis proposed that the facial image of a person could be obtained by thermal imaging technology, and then relevant analysis could be carried out to determine whether the person has fraudulent behavior [21].…”