Multiple thermal face detection in unconstrained environments has received increasing attention due to its potential in liveness detection and night-time surveillance. This paper presents an effective method based on ...
详细信息
ISBN:
(纸本)9783319773834;9783319773827
Multiple thermal face detection in unconstrained environments has received increasing attention due to its potential in liveness detection and night-time surveillance. This paper presents an effective method based on fully convolutional network (FCN), density-based spatial clustering of applications with noise (DBSCAN) and non-maximum suppression (NMS) algorithm. Our proposed approach captures the thermal face features automatically using FCN. Then, an improved DBSCAN is used to detect all the faces in the thermal images. Finally, we use NMS to remove all of the bounding-boxes with an IOU (intersection over union). Experiments on RGB-D-T database show that the proposed method exceeds the state-of-the-art algorithms for single face detection on thermal images. We also build a new database with 10K multiple thermal face images in unconstrained environments. The results also show a high precision for multi-face detection tasks.
The use of photovoltaics is still considered to be challenging because of certain reliability issues and high dependence on the global horizontal irradiance (GHI). GHI forecasting has a wide application from grid safe...
详细信息
The use of photovoltaics is still considered to be challenging because of certain reliability issues and high dependence on the global horizontal irradiance (GHI). GHI forecasting has a wide application from grid safety to supply-demand balance and economic load dispatching. Given a data set, a multi-layer perceptron neural network (MLPNN) is a strong tool for solving the forecasting problems. Furthermore, noise detection and feature selection in a data set with numerous variables including meteorological parameters and previous values of GHI are of crucial importance to obtain the desired results. This paper employs density-based spatial clustering of applications with noise (DBSCAN) and non-dominated sorting genetic algorithm II (NSGA II) algorithms for noise detection and feature selection, respectively. Tuning the neural network is another important issue that includes choosing the hidden layer size and activation functions between the layers of the network. Previous studies have utilized a combination of different parameters based on trial and error, which seems to be inefficient in terms of accurate selection of the desired features and also tuning of the neural network. In this research, two different methodsnamely, particle swarm optimization (PSO) algorithm and genetic algorithm (GA)are utilized in order to tune the MLPNN, and the results of one-hour-ahead forecasting of the GHI are subsequently compared. The methodology is validated using the hourly data for Elizabeth City located in North Carolina, USA, and the results demonstrated a better performance of GA in comparison with PSO. The GA-tuned MLPNN reported a normalized root mean square error (nRMSE) of 0.0458 and a normalized mean absolute error (nMAE) of 0.0238.
A system designed and developed for the three-dimensional (3-D) reconstruction of cultural heritage (CH) assets is presented. Two basic approaches are presented. The first one, resulting in an "approximate" ...
详细信息
A system designed and developed for the three-dimensional (3-D) reconstruction of cultural heritage (CH) assets is presented. Two basic approaches are presented. The first one, resulting in an "approximate" 3-D model, uses images retrieved in online multimedia collections;it employs a clustering-based technique to perform content-based filtering and eliminate outliers that significantly reduce the performance of 3-D reconstruction frameworks. The second one is based on input image data acquired through terrestrial laser scanning, as well as close range and airborne photogrammetry;it follows a sophisticated multistep strategy, which leads to a "precise" 3-D model. Furthermore, the concept of change history maps is proposed to address the computational limitations involved in four-dimensional (4-D) modeling, i.e., capturing 3-D models of a CH landmark or site at different time instances. The system also comprises a presentation viewer, which manages the display of the multifaceted CH content collected and created. The described methods have been successfully applied and evaluated in challenging real-world scenarios, including the 4-D reconstruction of the historic Market Square of the German city of Calw in the context of the 4-D-CH-World EU project. (C) 2016 SPIE and IS&T
Segmentation of the glottal area with high accuracy is one of the major challenges for the development of systems for computer-aided diagnosis of vocal-fold disorders. We propose a hybrid model combining conventional ...
详细信息
Segmentation of the glottal area with high accuracy is one of the major challenges for the development of systems for computer-aided diagnosis of vocal-fold disorders. We propose a hybrid model combining conventional methods with a superpixel-based segmentation approach. We first employed a superpixel algorithm to reveal the glottal area by eliminating the local variances of pixels caused by bleedings, blood vessels, and light reflections from mucosa. Then, the glottal area was detected by exploiting a seeded region-growing algorithm in a fully automatic manner. The experiments were conducted on videolaryngoscopy images obtained from both patients having pathologic vocal folds as well as healthy subjects. Finally, the proposed hybrid approach was compared with conventional region-growing and active-contour model-based glottal area segmentation algorithms. The performance of the proposed method was evaluated in terms of segmentation accuracy and elapsed time. The F-measure, true negative rate, and dice coefficients of the hybrid method were calculated as 82%, 93%, and 82%, respectively, which are superior to the state-of-art glottal-area segmentation methods. The proposed hybrid model achieved high success rates and robustness, making it suitable for developing a computer-aided diagnosis system that can be used in clinical routines. (C) 2017 SPIE and IS&T
Simultaneous detection of obstacles in the near field of the mobile robot is extremely urgent and complex task. In general, environment around robot is very complicated due to differences in change of lighting conditi...
详细信息
ISBN:
(纸本)9783319237664;9783319237657
Simultaneous detection of obstacles in the near field of the mobile robot is extremely urgent and complex task. In general, environment around robot is very complicated due to differences in change of lighting conditions and viewing angles. These problems lead to decrease accuracy of obstacles recognition. They can change quickly. However, obstacles must occupy a certain region in space. Kinect can be used for obtaining depth information. Kinect is a new camera system. The high cost of the depth-sensor for a long time prevented active implementation of these methods. However, with the appearance Microsoft Kinect can significantly be improved quality and efficiency of obstacles detection in autonomous robot navigation. Obtained depth images have normal resolution of 640x480 pixels at 30 frames per second. In this paper, we propose algorithms for obstacle detection with algorithm "3D-point cloud". Algorithm contains some main steps: Creation 3D-point cloud, transformation "2D-Point Cloud", obtaining results. Obstacles are detected based on their specific areas. 3D-point cloud are obtained from the depth data. Point clouds are usually defined as a set of unorganized irregular points in 3D. They not only save coordinates of all points in the near zone of mobile robot, but also additional data points (e.g., RGB color values, intensity, etc.). Algorithm clustering (DBSCAN) has shown in step "getting results" to increase accuracy. Obstacle detection efficiency is increased by using point clouds due to lower size of input data. Using 3D-point clouds allows satisfying requirements for obstacle detection in real time. The experimental results show the effectiveness of proposed approach using in vision system of a mobile robot platform.
暂无评论