This paper describes a vision-based tracking system using an autonomous Quadrotor Unmanned Micro-Aerial Vehicle (MAV). The vision-based control system relies on color target detection and tracking algorithm using integral image, Kalman filters for relative pose estimation, and a nonlinear controller for the MAV stabilization and guidance. The vision algorithm relies on information from a single onboard camera. An arbitrary target can be selected in real-time from the ground control station, thereby outperforming template and learning-based approaches. Experimental results obtained from outdoor flight tests, showed that the vision-control system enabled the MAV to track and hover above the target as long as the battery is available. The target does not need to be pre-learned, or a template for detection. The results from image processing are sent to navigate a non-linear controller designed for the MAV by the researchers in our group.
On ground stereo vision system is used for autonomous hovering and landing of a quadrotor Micro Aerial Vehicle (MAV). This kind of system has an advantage to support embedded vision system for autonomous hovering and landing, since an embedded vision system occasionally gives inaccurate distance calculation due to either vibration problem or unknown geometry of the landing target. Color based object tracking by using Continuously Adaptive Mean Shift (CAMSHIFT) algorithm was examined. Nonlinear model of quad-rotor MAV and a PID controller were used for autonomous hovering and landing. The result shows that the Camshift based object tracking algorithm has good performance. Additionally, the comparison between the stereo vision system based and GPS based autonomous hovering of a quad-rotor MAV shows that stereo vision system has better performance. The accuracy of the stereo vision system is about 1 meter in the longitudinal and lateral direction when the quad-rotor flies in 6 meters of altitude. In the same experimental condition, the GPS based system accuracy is about 3 meters. Additionally, experiment on autonomous landing gives a reliable result.
Oil palm (Elaeis guineensis) is considered as the most efficient and economic vegetable oil and has the capacity to fulfil the growing global need for oil consumption. The literature on oil palm pollination and its well-known pollinator Elaeidobius kamerunicus (EK), which performs natural pollination, is reviewed in consideration of extrinsic and intrinsic factors related with pollination effectiveness and palm oil production. The state of the oil palm and pollinators' interaction is demonstrated by illustrating the phenology and behaviour of the inflorescences. In addition, the effectiveness of weevils as a pollinator mostly differs within different localities, seasonal and climate changes. Nevertheless, oil palm pollination can be determined by studying the phenology changes of the plant's flowers changes during anthesis. This paper discusses the oil palm phenology studies related with weevils and the major factors that influence their performance as well as the application of recent pollination practices in oil palm plantations.
This paper describes the leader-follower formation control using two different approaches which are the PID leader-follower formation control (PID-LFFC) and Sliding Mode Control leader-follower formation control (SMC-LFFC). The strategy used in this paper is to apply the control algorithm for conducting a circular motion. This task is known to be important since a trajectory is a combination of movement. This movement can be divided into straight or curve lines. Curves lines or circular motion is essential for obstacle avoidance and also for turning movement. The curves lines or circular motion gives lower trajectory distance than only using straight or angled lines. Based on the experimental result, it is seen that the performance of the algorithm is reliable. When using SMC-LFFC over the PID-LFFC, the leader to follower distance error is 30% smaller and has a high 70% occurrence at 0 errors. Additionally, this research is known to be the first conducted in Japan.
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.