Studies of object detection have recently attracted increased interest. One of the applications of object detection is robotics. This paper present the real-time object detection integrated to humanoid robot soccer. In order to enhance the vision to detect ball and goal, the You Only Look Once (YOLO) methods is used as deep-learning object detection method. The real-time experiments have been carried out in LINUX OS by using NVIDIA JETSON TX1 controller board. The experimental results show that the proposed method capable to detect and distinguish objects in the different lighting condition, with interference from other objects, also from the different angle of capturing an image.

The deep learning-based object detector accuracy has surpassed conventional detection methods. Although implementation is still limited to hardware capabilities, this problem can be overcome by combining edge devices with cloud computing. The recent study of cloud-based object detector architecture is generally based on representational state transfer (RESTful web services), which uses a pooling system method for data exchange. As a result, this system leads to a low detection speed and cannot support real-time data streaming. Therefore, this study aims to enhance the detection speed in cloud-based object recognition systems using gRPC and Protobuf to support real-time detection. The proposed architecture was deployed on the Virtual Machine Instance (VMI) equipped with a Graphics Processing Unit (GPU). The gRPC server and YOLOv3 deep learning object detector were executed on the cloud server to handle detection requests from edge devices. Furthermore, the captured images from the edge devices were encoded into Protobuf format to reduce the message size delivered to the cloud server. The results showed that the proposed architecture improved detection speed performance on the client-side in the range of 0.27 FPS to 1.72 FPS compared to the state-of-the-art method. It was also observed that it could support multiple edge devices connection with slight performance degradation in the range of 1.78 FPS to 1.83 FPS, depending on the network interface used.

A humanoid robot called BarelangFC was designed to take part in the Kontes Robot Indonesia (KRI) competition, in the robot coordination division. In this division, each robot is expected to recognize its opponents and to pass the ball towards a team member to establish coordination between the robots. In order to achieve this team coordination, a fast and accurate system is needed to detect and estimate the other robot’s position in real time. Moreover, each robot has to estimate its team members’ locations based on its camera reading, so that the ball can be passed without error. This research proposes a Tiny-YOLO deep learning method to detect the location of a team member robot and presents a real-time coordination system using a ZED camera. To establish the coordinate system, the distance between the robots was estimated using a trigonometric equation to ensure that the robot was able to pass the ball towards another robot. To verify our method, real-time experiments was carried out using an NVDIA Jetson NX Xavier, and the results showed that the robot could estimate the distance correctly before passing the ball toward another robot.

The increasing number of vehicle causes the increasing of traffic density in which one of the main factors of congestion. Traffic density is usually alocated at certain points of roads, one at the instersection. In the novel technology, traffic in the crossroads had been controlled by traffic light using a traffic density prediction system. This prediction system would determine the duration of active green lights and red lights at each intersection. One of the most common prediction systems is a statistical estimation of vehicle density. Other method at controlling traffic density such as visually monitoring system might be implemented to increase system performance. Therefore, this research proposes an automatically traffic control system by predicting traffic density using image processing techniques. The proposed system is using a camera to visually monitor traffic condition. The image data obtained from the camera would be processed using an image processing and background subtraction techniques. This technique compared an the captured-image with a reference image to result a subtracted-image depicted the traffic density which is represented by the number of white pixels. Based on the number of white pixels that have been obtained, the percentage of vehicle queue length and vehicle density can be determine. The percentage then sent to the microcontroller in order to control the duration of the active green light. The traffic light control system using traffic density calculation has an accuracy of up to 77.03% while using the calculation of vehicle queue length reached 91.18%. Keywords : Image processing, image subtraction, light control system, traffic density, dilation, erosion
Abstrak Bertambahnya jumlah kendaraan menyebabkan meningkatnya kepadatan lalu lintas yang menjadi salah satu faktor utama penyebab kemacetan. Kepadatan lalu lintas biasanya teralokasi di beberapa titik-titik tertentu di ruas jalan, salah satunya di persimpangan. Saat ini lalu lintas di persimpangan jalan diatur oleh lampu lalu lintas menggunakan sistem prediksi kepadatan lalu lintas. Sistem prediksi ini nantinya akan menentukan lama aktifnya lampu hijau dan lampu merah di setiap persimpangan. Salah satu sistem prediksi yang banyak digunakan adalah metode estimasi stastistik kepadatan kendaraan. Metode lain pengontrolan kepadatan lalu lintas seperti sistem pemantauan secara visual memungkinkan untuk diterapkan guna menambah performansi sistem. Untuk itu penelitian ini mengusulkan pembuatan sebuah sistem pengontrolan lampu lalu lintas secara otomatis dengan prediksi kepadatan kendaraan menggunakan teknik pengolahan citra. Sistem yang dibangun menggunakan kamera untuk memantau kondisi kendaraan di jalan raya. Data gambar yang didapat dari kamera kemudian diolah menggunakan teknik pengolahan citra dan teknik pengurangan citra. Teknik ini membandingkan citra objek dengan citra referensi sehingga dapat diketahui jumlah piksel putih pada citra hasil pengurangan citra. Berdasarkan jumlah piksel putih yang telah diperoleh tersebut dapat diketahui persentase panjang antrian kendaraan dan kepadatan kendaraan. Data persentase yang diperoleh kemudian dikirim ke mikrokontroler untuk mengontrol durasi nyala lampu hijau. Pengontrolan lampu lalu lintas dengan perhitungan kepadatan kendaraan memiliki akurasi hingga 77.03% sedangkan dengan perhitungan panjang antrian kendaraan mencapai 91.18%. Kata Kunci : Pengolahan citra, pengurangan citra, sistem kontrol lampu, kepadatan kendaraan, dilation, erosion

This research study aims to develop automatic optical inspection (AOI) for detecting keycaps misplacement on the keyboard. The AOI hardware has been designed using an industrial camera with an additional mechanical jig and lighting system. Optical character recognition (OCR) using the Tesseract OCR engine is the proposed method to detect keycaps misplacement. In addition, captured images were cropped using a predefined region of interest (ROI) during the setup. Subsequently, the cropped ROIs were processed to acquire binary images. Furthermore, Tesseract processed these binary images to recognize the text on the keycaps. Keycaps misplacement could be identified by comparing the predicted text with the actual text on the golden sample. Experiments on 25 defects and 25 non-defected samples provided a classification accuracy of 97.34%, a precision of 100%, and a recall of 90.70%. Meanwhile, the character error rate (CER) obtained from the test on a total of 57 characters provided a performance of 10.53%. This outcome has implications for developing AOI for various keyboard products. In addition, the precision level of 100% signifies that the proposed method always offers correct results in detecting product defects. Such outcomes are critical in industrial applications to prevent defective products from circulating in the market.

Conducting robotics training as a community service to improve basic knowledge of Science, Technology, Engineering, and Mathematics (STEM) for students is one of the ways to improve their basic knowledge of Science, Technology, Engineering, and Mathematics (STEM) for students is one of the most important aspects of the facing the industrial era 4.0 and society 5.0. Through the Service-Learning approach, this community service by collaborating with Granada International in Batam by involving 29 students, consisting of 7 students from class X, 15 students from class XI, and the rest from class XII, class XI students, and the rest from class XII. The results of mentoring through robotics training were able to increase the average STEM skills of students by 38.15%. In addition, the activity was successfully implemented with participant satisfaction levels above 50% for the subject matter, instructor, and training equipment. Only 17% of the trainees stated that the training time was insufficient, especially for practicum.