Object detection is an advanced area of image processing and computer vision. Its major applications are in surveillance, autonomous driving, face recognition, anomaly detection, traffic management, agriculture etc. This paper focuses on various object detection techniques in thermal images. A thermal imaging sensor is a device that creates an image by analyzing temperature differences between different objects in a scene and detecting radiation from those objects. In recent years, many machine learning and deep learning algorithms have been used to recognize objects in thermal images. This study makes a comparison of YOLO, YOLO DarkNet, Retinex algorithm, CNN-based machine learning model Support Vector Machine (SVM), and Gaussian Mixture Model (GMM), Mixer of Gaussian (MoG), Mean Shift Approach, Faster R-CNN and Deep Neural Network along with different datasets.
Automatic Image Mining qwertyforce.dev - get the latest breaking news, showbiz & celebrity photos, sport news & rumours, viral videos and top stories from qwertyforce.dev Daily Mail and Mail on Sunday newspapers.
Driver cognitive fatigue can significantly affect driving and may lead to fatal accidents. In this regard, automatic detection of underload driver cognitive fatigue based on upper body posture dynamics is studied in this paper, where a semi-supervised approach is developed to identify the cognitive fatigue patterns of driver posture. Initially, an unsupervised Gaussian Mixture Model (GMM) clustering is applied to the acceleration data representing the driver's head, neck, and sternum obtained in a simulated driving through a motion capture suit. This provides the optimum clusters of the most-similar and correlated time-series data of driver upper posture. Then, an automatic labelling algorithm is developed that mines the maximal value and the standard deviation of each GMM cluster and assigns a symbol according to the discrepancy in postural behaviour. Finally, novel machine learning supervised classifiers, including Gaussian Support Vector Machines, and Bootstrap-Aggregating base
This paper considers energy delivery by a Hybrid Access Point (HAP) to one or more Radio Frequency (RF)-energy harvesting devices. Unlike prior works, it considers imperfect and causal Channel State Information (CSI), and probabilistic constraints that ensure devices receive their required amount of energy over a given planning horizon. To this end, it outlines two novel contributions. The first is a chance-constrained program, which is then solved using a Mixed Integer Linear Program (MILP) coupled with a Sample Average Approximation (SAA) method. The second is a Model Predictive Control (MPC) solution that utilizes Gaussian Mixture Model (GMM) and a so called backoff that is used to tighten probabilistic constraints. The results show that the performance of the MPC based solution is within 8% of the optimal solution with a probability of 90.8%.