Recently, many researchers have attempted to use convolutional neural networks (CNNs) for wildfire smoke detection. However, the application of CNNs in wildfire smoke detection still faces several issues, e.g., the high false-alarm rate of detection and the imbalance of training data. To address these issues, we propose a novel framework integrating conventional methods into CNN for wildfire smoke detection, which consisted of a candidate smoke region segmentation strategy and an advanced network architecture, namely wildfire smoke dilated DenseNet (WSDD-Net). Candidate smoke region segmentation removed the complex backgrounds of the wildfire smoke images. The proposed WSDD-Net achieved multi-scale feature extraction by combining dilated convolutions with dense block. In order to solve the problem of the dataset imbalance, an improved cross entropy loss function, namely balanced cross entropy (BCE), was used instead of the original cross entropy loss function in the training process. The proposed WSDD-Net was evaluated according to two smoke datasets, i.e., WS and Yuan, and achieved a high AR (99.20%) and a low FAR (0.24%). The experimental results demonstrated that the proposed framework had better detection capabilities under different negative sample interferences.
Path planning of unmanned aerial vehicles (UAVs) in threatening and adversarial areas is a constrained nonlinear optimal problem which takes a great amount of static and dynamic constraints into account. Quantum-behaved pigeon-inspired optimization (QPIO) has been widely applied to such nonlinear problems. However, conventional QPIO is suffering low global convergence speed and local optimum. In order to solve the above problems, an improved QPIO algorithm, adaptive operator QPIO, is proposed in this paper. Firstly, a new initialization process based on logistic mapping method is introduced to generate the initial population of the pigeon-swarm. After that, to improve the performance of the map and compass operation, the factor parameter will be adaptively updated in each iteration, which can balance the ability between global and local search. In the final landmark operation, the gradual decreasing pigeon population-updating strategy is introduced to prevent premature convergence and local optimum. Finally, the demonstration of the proposed algorithm on UAV path planning problem is presented, and the comparison result indicates that the performance of our algorithm is better than that of particle swarm optimization (PSO), pigeon-inspired optimization (PIO), and its variants, in terms of convergence and accuracy.
VLP leaded to significantly better results of reduction maintainance and the final joint congruity than NLP, while reducing overall and major complications. However, the results should be treated in the context of limitations and the clinical significance of the difference required further studies to investigate.
We proposed a novel saliency detection method based on histogram contrast algorithm and images captured with WMSN (wireless multimedia sensor network) for practical wild animal monitoring purpose. Current studies on wild animal monitoring mainly focus on analyzing images with high resolution, complex background, and nonuniform illumination features. Most current visual saliency detection methods are not capable of completing the processing work. In this algorithm, we firstly smoothed the image texture and reduced the noise with the help of structure extraction method based on image total variation. After that, the saliency target edge information was obtained by Canny operator edge detection method, which will be further improved by position saliency map according to the Hanning window. In order to verify the efficiency of the proposed algorithm, field-captured wild animal images were tested by using our algorithm in terms of visual effect and detection efficiency. Compared with histogram contrast algorithm, the result shows that the rate of average precision, recall and F-measure improved by 18.38%, 19.53%, 19.06%, respectively, when processing the captured animal images.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.