This paper presents a novel 3D feature descriptor for object recognition and to identify poses when there are six-degrees-of-freedom for mobile manipulation and grasping applications. Firstly, a Microsoft Kinect sensor is used to capture 3D point cloud data. A viewpoint feature histogram (VFH) descriptor for the 3D point cloud data then encodes the geometry and viewpoint, so an object can be simultaneously recognized and registered in a stable pose and the information is stored in a database. The VFH is robust to a large degree of surface noise and missing depth information so it is reliable for stereo data. However, the pose estimation for an object fails when the object is placed symmetrically to the viewpoint. To overcome this problem, this study proposes a modified viewpoint feature histogram (MVFH) descriptor that consists of two parts: a surface shape component that comprises an extended fast point feature histogram and an extended viewpoint direction component. The MVFH descriptor characterizes an object’s pose and enhances the system’s ability to identify objects with mirrored poses. Finally, the refined pose is further estimated using an iterative closest point when the object has been recognized and the pose roughly estimated by the MVFH descriptor and it has been registered on a database. The estimation results demonstrate that the MVFH feature descriptor allows more accurate pose estimation. The experiments also show that the proposed method can be applied in vision-guided robotic grasping systems.

Accelerated urbanization and the ensuing rapid increase in urban populations led to the need for a tremendous number of parking spaces. Automated parking systems coupled with new parking lot layouts can effectively address the need. However, most automated parking systems available on the market today use ultrasonic sensors to detect vacant parking spaces. One limitation of this method is that a reference vehicle must be parked in an adjacent space, and the accuracy of distance information is highly dependent on the positioning of the reference vehicle. To overcome this limitation, an around view monitoring-based method for detecting parking spaces and algorithms analyzing the vacancy of the space are proposed in this study. The framework of the algorithm comprises two main stages: parking space detection and space occupancy classification. In addition, a highly robust analysis method is proposed to classify parking space occupancy. Two angles of view were used to detect features, classified as road or obstacle features, within the parking space. Road features were used to provide information regarding the possible vacancy of a parking space, and obstacle features were used to provide information regarding the possible occupancy of a parking space. Finally, these two types of information were integrated to determine whether a specific parking space is occupied. The experimental settings in this study consisted of three common settings: an indoor parking lot, an outdoor parking lot, and roadside parking spaces. The final tests showed that the method’s detection rate was lower in indoor settings than outdoor settings because lighting problems are severer in indoor settings than outdoor settings in around view monitoring (AVM) systems. However, the method achieved favorable detection performance overall. Furthermore, we tested and compared performance based on road features, obstacle features, and a combination of both. The results showed that integrating both types of features produced the lowest rate of classification error.

This research proposed a novel global maximum power point tracking (global-MPPT) algorithm. The proposed algorithm eliminates the perturbation and observation (P&O) technique disturbance problem that the power point will be stuck at the local peak power point under a partial shading condition (PSC). The proposed global-MPPT algorithm detects the photovoltaic module (PV-M) environment irradiance level by the relationship between the output power and voltage of the PV-M. In the proposed algorithm, the important parameter w is determined by the PV-M output power and irradiance level, which is also the compensation parameter that corresponds to the relationship of temperature. The proposed global-MPPT algorithm is aimed to predict the best duty cycle of the global-MPPT based on the irradiance level, parameter w, PV-M output voltage, and load, and then achieve the maximum power point (MPP) quickly and accurately. The measurement results under UIC and PSC verify that the proposed global-MPPT technique performs better than the particle swarm optimization (PSO) and P&O techniques. This research contributes to the proposed method that can find the global-MPP in time based on the irradiance level, temperature, and load.

Distracted driving is the most common cause of traffic accidents. According to a World Health Organization report, the number of traffic accidents has been increasing in recent years. To address this issue, distracted-driving recognition is an important area of traffic safety research. However, distracted behavior may be a part of a driver’s regular tasks. For example, sometimes a delivery person must use his/her phone while driving. The use of walkie-talkies is required for container-truck drivers because they improve unloading efficiency and reduce the time cargo ships spend in a port, resulting in cost savings. While driving on the highway, it is sometimes necessary to tune the radio to receive an update on road conditions. Furthermore, drinking water is permitted while waiting for a traffic signal for an extended period of time. Therefore, for the distracted-driving alert system, the driving scenario is important. To address this issue, we present a novel framework herein that combines driving perception and driver behavior recognition to provide the driver with appropriate warnings. By combining driver perception and behavior recognition, our proposed framework can reduce false alerts. We also define different time-to-collision standards to achieve humane and effective warnings. We try to study various behaviors and define various time-to-collision standards for making safety-level decisions. For driving perception and driver behavior recognition, a modified convolutional neural network is used, which alerts the driver immediately.

Traffic flow prediction is very important for real time information of travelers and dynamic route guidance system. In the past, various methodologies have been developed for traffic flow prediction. However, most of existing methods for the formulation of traffic flow are complex. In this paper, using a 2-D histogram projection method, a temporal-spatial traffic flow data is first reduced to a 2-D scatter plot and a 2-D Gaussian Mixture Modeling (GMM) is then used to estimate the traffic flow. This study shows that the traffic flow data can be simply represented by a linear combination of multiple Gaussian functions which demonstrates a good visualization of the temporal-spatial traffic flow data.

A convolutional neural network (CNN) that was trained using datasets for multiple scenarios was proposed to facilitate real-time road semantic segmentation for various scenarios encountered in autonomous driving. However, the CNN inhibited the mutual suppression effect between weights; thus, it did not perform as well as a network that was trained using a single scenario. To address this limitation, we used a model-switching architecture in the network and maintained the optimal weights of each individual model which required considerable space and computation. We, subsequently, incorporated a lightweight process into the model to reduce the model size and computational load. The experimental results indicated that the proposed lightweight CNN with a model-switching architecture outperformed and was faster than the conventional methods across multiple scenarios in road semantic segmentation.