Rapid Foreign Object Detection System on Seaweed Using VNIR Hyperspectral Imaging.

The consumption of seaweed is increasing year by year worldwide. Therefore, the foreign object inspection of seaweed is becoming increasingly important. Seaweed is mixed with various materials such as laver and sargassum fusiforme. So it has various colors even in the same seaweed. In addition, the surface is uneven and greasy, causing diffuse reflections frequently. For these reasons, it is difficult to detect foreign objects in seaweed, so the accuracy of conventional foreign object detectors used in real manufacturing sites is less than 80%. Supporting real-time inspection should also be considered when inspecting foreign objects. Since seaweed requires mass production, rapid inspection is essential. However, hyperspectral imaging techniques are generally not suitable for high-speed inspection. In this study, we overcome this limitation by using dimensionality reduction and using simplified operations. For accuracy improvement, the proposed algorithm is carried out in 2 stages. Firstly, the subtraction method is used to clearly distinguish seaweed and conveyor belts, and also detect some relatively easy to detect foreign objects. Secondly, a standardization inspection is performed based on the result of the subtraction method. During this process, the proposed scheme adopts simplified and burdenless calculations such as subtraction, division, and one-by-one matching, which achieves both accuracy and low latency performance. In the experiment to evaluate the performance, 60 normal seaweeds and 60 seaweeds containing foreign objects were used, and the accuracy of the proposed algorithm is 95%. Finally, by implementing the proposed algorithm as a foreign object detection platform, it was confirmed that real-time operation in rapid inspection was possible, and the possibility of deployment in real manufacturing sites was confirmed.

On the Deployment and Noise Filtering of Vehicular Radar Application for Detection Enhancement in Roads and Tunnels.

Recently, radar technology has attracted attention for the realization of an intelligent transportation system (ITS) to monitor, track, and manage vehicle traffic on the roads as well as adaptive cruise control (ACC) and automatic emergency braking (AEB) for driving assistance of vehicles. However, when radar is installed on roads or in tunnels, the detection performance is significantly dependent on the deployment conditions and environment around the radar. In particular, in the case of tunnels, the detection accuracy for a moving vehicle drops sharply owing to the diffuse reflection of radio frequency (RF) signals. In this paper, we propose an optimal deployment condition based on height and tilt angle as well as a noise-filtering scheme for RF signals so that the performance of vehicle detection can be robust against external conditions on roads and in tunnels. To this end, first, we gather and analyze the misrecognition patterns of the radar by tracking a number of randomly selected vehicles on real roads. In order to overcome the limitations, we implement a novel road watch module (RWM) that is easily integrated into a conventional radar system such as Delphi ESR. The proposed system is able to perform real-time distributed data processing of the target vehicles by providing independent queues for each object of information that is incoming from the radar RF. Based on experiments with real roads and tunnels, the proposed scheme shows better performance than the conventional method with respect to the detection accuracy and delay time. The implemented system also provides a user-friendly interface to monitor and manage all traffic on roads and in tunnels. This will accelerate the popularization of future ITS services.