Search

Masa pandemi Covid-19 mengharuskan anak-anak siswa sekolah dasar dan menengah melaksanakan aktivitas pembelajaran secara daring di rumah. Dalam praktiknya, anak-anak menjadi lebih sering berinteraksi dengan gawai, baik pada jam sekolah daring maupun di luar jam tersebut. Hal ini menjadi kekhawatiran sebagian besar masyarakat perumahan Graha Nusa Batam, sebab anak-anak di sana sudah mulai memiliki gejala kecanduan gawai. Dengan latar belakang permasalahan tersebut, tim dari Politeknik Negeri Batam (Polibatam) mengadakan program workshop teknologi robotika untuk anak usia 8-15 tahun. Tujuan kegiatan ini adalah meningkatkan pemahaman anak mengenai teknologi robotika yan meliputi elektronika dan mekanika. Selain tujuan tersebut, kegiatan ini memberikan beberapa manfaat, antara lain sebagai alternatif kegiatan yang menarik bagi anak-anak agar tidak selalu bermain gawai, memberikan pengalaman anak-anak dalam hal problem solving, kreativitas, dan kolaborasi, dan memberikan pengalaman lapangan kepada mahasiswa Polibatam dengan mengaplikasikan ilmu yang diperoleh melalui Problem Based Learning (PBL) untuk kepentingan masyarakat. Workshop ini dilakukan dalam empat pertemuan (Maret hingga April 2021), bertempat di gedung Taman Pendidikan Al Qur’an (TPA) At Taqwa, perumahan Graha Nusa Batam. Robot yang digunakan adalah line follower analog. Pre-test dan post-test dilakukan untuk mengukur peningkatan pemahaman peserta terhadap materi. Hasil tes ini menunjukkan bahwa melalui workshop ini pemahaman peserta mengenai teknologi robotika dapat meningkat hingga 25% untuk peserta berusia 8-11 tahun dan 22% untuk peserta berusia 12-15 tahun

Salah satu minuman kemasan yang banyak dipakai adalah kemasan kaleng. Kekurangan kemasan minuman kaleng adalah sifatnya yang mudah rusak akibat benturan dengan benda lain maupun terjatuh. Kemasan yang rusak mengakibatkan produk menjadi tidak sempurna. Sehingga proses identifikasi kerusakan kemasan kaleng menjadi sangat penting sebagai proses penjamin kualitas produk. Penelitian ini ditujukan sebagai salah satu solusi untuk mengidentifikasi kerusakan pada kemasan minuman kaleng. Metode deteksi yang diusulkan berdasarkan pada deteksi tepi Canny dan RMSE (Root Mean Square Error). Proses awal deteksi dimulai dengan pengkapturan citra kaleng oleh kamera. Citra asli RGB ini akan dikonversi ke citra biner untuk kemudian dilakukan deteksi tepi Canny. Pada penelitian ini, digunakan nilai high threshold 20 dan low threshold 10 pada proses deteksi tepi Canny. Citra hasil deteksi tepi Canny akan dibandingkan dengan citra deteksi Canny yang menjadi referensi menggunakan nilai RMSE. Nilai RMSE yang digunakan untuk kategori OK dan NG dibatasi pada nilai 70. Hasil pengujian menunjukan nilai RMSE untuk kategori OK berada pada rentang 70.72 dan 85.24 sedangkan kategori NG berada pada rentang 47.99 dan 69.93. Pengujian dilakukan menggunakan citra kaleng bagian atas dan tengah.

Peningkatan jumlah pengendara yang begitu pesat yang belum mampu di tangani oleh fasilitas jalan berefek pada masalah pelanggaran lalu lintas yang menimbulkan banyak korban. Untuk mengurangi masalah pelanggaran lalu lintas tersebut, dibutuhkan sistem pendeteksi pelanggaran yang dapat mempermudah petugas dalam memantau terjadinya pelanggaran di persimpangan lampu lalu lintas. Pada penelitian ini telah dikembangkan sistem deteksi pelanggaran pada simpang lampu lalu lintas. Sistem dirancang dengan menggunakan tiga tahapan yaitu deteksi lampu hijau, deteksi kendaraan dan deteksi jumlah pelanggaran. Pada tahap pertama yaitu deteksi lampu hijau digunakan filter warna HSL yang akan mendeteksi warna hijau dari lampu lalu lintas. Untuk mendeteksi kendaraan digunakan metode background substraction, morphology filer dan blob detection. Tahapan terakhir adalah mendeteksi jumlah pelanggaran yang ditentukan dengan penentuan garis virtual yang ditempatkan di atas zebra cross. Pada tahap ini, pelanggaran ditentukan oleh pengendara yang melewati garis virtual atau berada di atas garis virtual. Sistem diimplementasikan menggunakan video hasil rekaman di beberapa simpang lalu lintas. Sistem yang dikembangkan telah berhasil mendeteksi jumlah pelanggar yang menerobos lampu lalu lintas. Hasil pengujian menunjukkan bahwa sistem deteksi pelanggaran telah berhasil mendeteksi pelanggaran dengan tingkat kesalahan rata-rata sebesar 1,1%.

Salah satu tantangan dalam budi daya tanaman adalah masalah penyiraman tanaman. Sebagian besar proses penyiraman dilakukan secara konvensional. Penelitian ini mengusulkan salah satu pemecahan masalah penyiraman dengan suatu sistem kontrol penyiraman tanaman otomatis menggunakan logika fuzzy. Sistem yang diusulkan dengan menggunakan dua kriteria yaitu kondisi udara (suhu) dan kondisi tanah (kelembaban). Sistem yang dikembangkan menghasilkan keluaran berupa durasi waktu penyiraman dalam empat kriteria yaitu sangat cepat, cepat, sedang dan lama. Hasil pengujian terhadap kondisi suhu menunjukan error rata-rata sebesar 0.41%, sedangkan pengujian kelembaban menunjukan error rata-rata sebesar 2.3%. Rata-rata durasi waktu penyiraman yang dihasilkan oleh sistem adalah 33.1 detik.

Dengan sedikitnya pengetahuan tentang nama buah yang didapat sebelumnya, tidak sedikit anak-anak maupun dewasa yang tidak mengetahui jenis maupun nama suatu buah terutama jika buah tersebut adalah buah yang langka. Selain itu kebutuhan akan alat ukur sangatlah tinggi sebanding dengan kebutuhan akan bahan pangan itu sendiri. Alat ukur yang tersedia hanyalah alat ukur yang menimbang berat buah tanpa dapat memperkirakan harga. Sehingga keberadaan akan alat ukur yang dapat mengukur berat sekaligus menampilkan harga sangatlah dibutuhkan. Dalam penelitian ini dikembangkan sistem yang menjawab kebutuhan akan sistem yang dapat memprediksi berat buah dan harga buah. Proses prediksi berat buah dilakukan dengan perhitungan jumlah pixel dan dianalisa menggunakan persamaan regresi. Hasil perkiraan berat buah ini menghasilkan eror berat rata-rata 4.44%. Sementara proses perkiraan harga buah didapat dari perkiraan bobot buah dikalikan harga per berat buah masing-masing. Hasil perkiraan harga buah ini menghasilkan eror harga buah rata-rata 5.64 %.

Kekasaran permukaan logam merupakan salah satu parameter yang dapat dijadikan acuan dalam penilaian mutu suatu logam. Nilai kekasaran permukaan suatu bahan logam dapat dilakukan dengan pendekatan matematik dan pengukuran. Pada penelitian ini, kajian mengenai kekasaran permukaan suatu logam dilakukan dengan menggunakan pengukuran langsung dan menggunakan analisis citra gambar. Adapun teknik pengukuran langsung dilakukan dengan menggunakan Surftest pada 20 titik (5 titik dari diagonal sisi kanan, 5 titik diagonal sisi kiri, 5 titik vertikal dan 5 titik horizontal) sedangkan analisis citra gambar dilakukan dengan menggunakan Image-J pada foto gambar permukaan besi. Berdasarkan metode penelitian yang telah dilakukan diperoleh kesimpulan yaitu semakin besar nilai grit abrasive paper yang digunakan pada permukaan besi, maka nilai kekasaran permukaan besi semakin kecil/semakin halus (nilai kekasaran permukaan cenderung menurun). Sedangkan hasil pengolahan citra gambar yang dilakukan dengan Image-J telah berhasil menunjukan surface plot permukaan sampel besi. Selain dari itu, gray value dari citra gambar yang dihasilkan mengalami fluktuasi seiring dengan semakin panjang/besarnya distance (pixels).

Dalam artikel ini dibahas tentang studi komparasi deteksi dan pelacakan(tracking) objek menggunakan filter warna. Filter warna yang digunakan adalah filter warna RGB, HSL dan YCbCr. Proses pelacakan diawali dengan proses pengambilan citra dengan kamera secara real time. Proses kedua adalah proses deteksi menggunakan salah satu filter warna. Pada proses ini, objek dipisahkan dari latarnya menggunakan nilai ambang (threshold) pada tiap komponen filter. Sehingga object dengan warna tertentu saja yang terdeteksi. Proses selanjutnya adalah proses pelacakan oleh tiap filter warna. Komparasi dilakukan dengan menganalisa hasil deteksi dan pelacakan tiap filter warna.. Hasil eksperimen menunjukkan urutan akurasi deteksi objek dengan filter warna adalah HSL, YCbCr dan RGB dengan error rata-rata 7%, 9% dan 10%. Sementara untuk akurasi pelacakan objek dengan filter warna adalah HSL, YCbCr dan RGB dengan error rata-rata 11%, 13% dan 22%. Nilai maksimum error baik untuk deteksi maupun pelacakan terjadi pada objek dengan warna yang mirip dengan warna latar. Ini terjadi pada filter warna RGB

Elektrokardiograf (ECG) yang bersifat wearable dan nirkabel telah banyak digunakan untuk monitoring jangka panjang karena alasan praktis. Selain Signal to Noise Ratio (SNR) yang tinggi, salah satu manfaat ECG dalam bentuk patch adalah fleksibilitasnya bagi pengguna dalam menempatkan elektroda. Sebagian besar ECG patch nirkabel komersial yang ada di pasaran hanya dapat menampilkan Heart Rate Variability (HRV) saja, tanpa kemampuan untuk menyediakan atau merekam gelombang EKG. Beberapa produk komersial menggunakan dua elektroda saja: Right Arm (RA) dan Left Arm (LA), tanpa elektroda tambahan yang disebut Right Arm Drive (RLD). Selain itu, menyediakan lebih dari satu opsi teknologi nirkabel untuk ECG patch merupakan keuntungan tambahan. Pada penelitian ini, kami membuat ECG patch nirkabel berbiaya rendah yang memiliki kemampuan untuk menyediakan bentuk gelombang EKG (Lead I) dan menghitung HRV secara otomatis. Selain RA dan LA, alat ini menggunakan elektroda RLD untuk meningkatkan Common Mode Rejection Ratio (CMRR). Untuk pemrosesan data, kami menggunakan ESP32, mikrokontroler 32-bit berdaya rendah yang dilengkapi dengan Bluetooth Classic (BT), Bluetooth Low Energy (BLE), dan Wifi dalam modul yang ringkas. Hasil tes menunjukkan bahwa ECG patch yang dibuat menghasilkan perhitungan HRV yang lebih akurat serta waktu transisi 2,7 kali lebih cepat dibandingkan dengan produk komersial yang kami jadikan referensi.

Etsa FeCl3 merupakan proses menghilangkan bagian tertentu dari suatu material dengan menggunakan FeCl3 dengan konsentrasi minimum 28%. Metode yang digunakan dengan larutan FeCl3 adalah metode reaksi kimia dengan bahan yang digunakan adalah PCB. Penelitian ini bertujuan untuk mengetahui pengaruh 3 variasi yang digunakan terhadap kehilangan massa PCB dan waktu etsa PCB. Variasi karakterisasi yang digunakan yaitu plat PCB yang dietsa dengan menggunakan pemanasan dan stirer (PS), Plat PCB yang dietsa dengan menggunakan pemanasan tanpa menggunakan stirer (PTS) dan Plat PCB yang dietsa tanpa menggunakan pemanasan dan stirer (TPTS). Setelah dilakukan proses etsa, plat PCB dikarakterisasi menggunakan Mikroskop Optik Motik SMZ168. Berdasarkan penelitian yang telah dilakukan, plat PS memiliki nilai kehilangan massa yang lebih tinggi jika dibandingkan dengan PTS dan TPTS. Waktu yang dibutuhkan untuk proses etsa PS terjadi pada waktu 5 menit lebih cepat dibandingkan dengan PTS yang berlangsung selama 10 menit dan TPTS yang berlangsung selama 20 menit

Kemajuan teknologi pengolahan citra digital banyak dimanfaatkan oleh manusia. Manfaat pengolahan citra di antaranya adalah untuk meningkatkan kualitas suatu citra, menghilangkan cacat pada citra dan mengidentifikasi objek. Dengan memanfaatkan teknologi tersebut, dapat dikembangkan suatu sistem yang dapat mendeteksi objek serta melakukan tracking. Pada Tugas akhir ini penulis akan membuat sebuah sistem untuk mendeteksi objek berwarna. Metode untuk mendeteksi warna penulis menggunakan filter warna HSV, metode erosi, dilasi dan thresholding. Untuk membaca jarak robot terhadap objek, digunakan metode Regresi yang nantinya akan digunakan sebagai penggerak bagi aktuator motor dc. Hasil yang dicapai dalam penelitian ini adalah sistem dapat mendeteksi objek pada jarak 50-180 cm dan mengikutinya pada jarak 60-150 cm.

Artikel ini bertujuan membandingkan filter warna RGB, HSL dan YCbCr dalam mendeteksi dan melacak wajah berbasis partikel filter. Citra wajah yang ditangkap kamera secara real time akan diproses menggunakan filter warna RGB, HSL, dan YCbCr. Citra wajah akan dideteksi dengan mengatur interval kombinasi tiap elemen warna dari filter warna yang digunakan. Setelah citra wajah berhasil dideteksi, proses selanjutnya adalah pelacakan wajah menggunakan partikel filter. Metode partikel filter terdiri dari beberapa tahap, diantaranya proses inisialisasi yang dilakukan dengan cara menyebar partikel secara acak di sekitar citra wajah, prediksi dan update partikel, resampling partikel dan proses estimasi berdasarkan posisi rata-rata partikel. Hasil pengujian menunjukkan perbandingan kesalahan pelacakan dengan jumlah partikel 50, 70 dan 100 pada sumbu X dan Y adalah (3.30; 2.11), (2.62; 1.70) dan (1.34; 1.21) menggunakan filter RGB, (3.72; 1.92), (2.50; 1.81) dan (1.85; 1.42) menggunakan filter HSL, dan (12.97; 5.01), (23.07; 5.11) dan (25.51; 3.57) menggunakan filter YCbCr.

Etching is one of the processes in manufacturing a multilayer PCB. It is a crucial process in which certain metal parts on the multilayer PCB are removed by using particular chemicals. However, this process can cause over-etching or loss of certain multilayer PCB lines, which is definitely unexpected in the manufacturing process of PCB. Based on this problem, this research aims to study the concentrations of the etching solutions applied in the etching process of the multilayer PCB lines. Specifically, the authors conduct a study on the use of Ferric Chloride 38 wt% (FC38) and Ferric Chloride 34 wt% (FC34) as chemical solutions applied. Results show that the highest error value percentage of FC38 at 6 minutes is on line 0.2 mm and the highest error value percentage of FC38 at 14 minutes is on line 0.5 mm. Meanwhile, the highest error value percentage of FC34 at 6 minutes is on line 0.2 mm and the the highest error value percentage of FC34 at 14 minutes is on line 0.1 mm. Furthermore, clearance values of all PCB lines due to the use of FC38 and FC34 are not sufficient to meet the Altium software recommendation.

The quality of production in a company is a major guarantee. It needed a human resources, assistance company to control the product quality. However, human errors causing product failures are still found in many cases. Some disadvantages of using human power for the inspection process are fatigued in the eye when carrying out inspections using manual equipment such as magnifying glasses and microscopes. So in this study a system was designed to detect and identify anomalies on the soldering of ICSOIC on surface mount devices using image processing and neural networks. To separate the soldering colour from the SOIC IC, the HSL method is used while the identification of the type of anomaly in the SOIC IC used a backpropagation neural network. From the results of the system testing carried out, the success rate reached 92.72% from 11 trials.

Localization is a method used to determine the position of an object. In mobile robots, especially wheeled soccer robots, determining the location of robots against landmarks is needed. It can determine the movements and strategies of soccer robots in a game. There are several methods can be used for localization, namely the odometry method and the extended Kalman filter. But the methods are strongly influenced by the results of reading sensors and tire slips on the robots. In this article, we proposed a particle filter algorithm for localization of wheeled soccer robots. This particle filter method is suitable for non-linear, non-Gaussian systems, and can be used in a real-time environment. We applied the particle filter algorithm to localize the position of the wheeled soccer robot. The particle filter algorithm generally has three basic stages, prediction stage, weight update and resampling. As initialization process, the particles are spread randomly or around the initial position of the robot. The prediction stage is done during the robot movement using a motion model applied to each particle. After that, the weight of each particle is updated based on the likelihood of particle data to the robot data. The resampling step is performed to update the weight of each particle. Particles with the smallest weight value will disappear by themselves and particles with large weight will retain. The position presumption is obtained through the estimation process that is by averaging the position of all particles. The experiment is done using simulation on the field with 450 × 300 pixels or 900 × 600 cm which each pixel represent 2 cm on the real soccer for competition. The particles used in the experiment are 100, 200, 400, 800, and 1600 particles. The experiment results show the satisfied result with number of particles error is 100 particles and the error is between 0.363 cm and 23.055 cm.

The main goal of this study is to detect the landmark of football fields with a real-time object recognition system based on deep neural networks. The deep neural networks used are YOLO (You Only Look Once). The deep learning of YOLO can detect and recognize objects robustly in a high speed. By using this method, the robot can robustly detect and recognize the landmark of football fields in images with size of 608 × 608 pixels at 16 frames per second with MAP (Mean Average Precision) and IoU (Intersect over Union) with 97.60% and 81.36% accuracy.

This paper presented a face recognition method based on PCA and Back Propagation Neural Network which is robust and simple algorithm based on image captured by camera. The proposed algorithm is done on three stages, namely face detection, face feature extraction and face recognition. The face detection is performed using Haar-Like Feature. The Haar-Like feature analyzes the pixels in the image into squares by function. The method uses the Adaboost learning algorithm to select a small number of important feature from a large data set. The detected face is then extracted using PCA. PCA will select and reduce the face feature based on eigenvalues of correlation matrix data. We obtain 500 features face extracted using PCA. The face feature becomes the input to neural network for recognition process. The neural network is developed with two hidden layers with 15 nodes on each and three nodes of output layer. The experiment is performed in real time environment. Using 5 faces image data with each data is taken 100 times, the experimental result showed the satisfactory result with 87.5% recognition rate in average.

This research aimed to develop an algorithm to classify an object based on color, shape and dimension. In this research, the classification process was designed on two combined features which are color-shape, color-dimension, and shape-dimension. Each two combined features yielded 9 classification results. Therefore, in total, the number of classifications of three combined features were 27 classifications. The algorithm was depeloved as follows. The color feature was classiffied using RGB color histogram. Each object histogram was compared and calculated the distance to the reference object histogram. The similarity was determined with the smaller distance to the reference object. The shape feature was classified using shape matching algorihtm. The algorithm measured the similarity based on distance between two point on each geometry. The dimension feature was classified using the number of the pixel on each object. The number of pixel was callibrated on certain distance to the camera. The algoritma was also designed to classify the reject object (Not Good/NG). The algortihm was implemented on a conveyor system as a sorting machine. The conveyor has 10 output classification, 9 output for object classification and 1 output for NG object. The experimental results showed the sistem could classify the object in 27 category classification and 1 NG category.Keywords: object cleassification, object feature, RGB color histogram, shape matching, object sortingABSTRAKPenelitian ini bertujuan untuk membangun algoritma untuk pengklasifikasian objek berdasarkan warna, bentuk dan dimensi. Dalam penelitian ini, pengklasifikasian didesain dalam dua ciri gabungan yaitu warna-bentuk, warna-dimensi dan bentuk-dimensi. Tiap-tiap dua ciri gabungan tersebut akan menghasilkan 9 hasil klasifikasi. Sehingga total klasifikasi gabungan 3 ciri adalah 27 klasifikasi. Algoritma yang dikembangkan untuk masing-masing ciri adalah sebagai berikut. Ciri warna diklasifikasikan menggunakan histogram warna RGB. Tiap objek dibandingkan histogramnya dan dihitung jarak tiap histogram dengan histogram referensi. Semakin dekat dengan histogram referensi, maka objek tersebut diklasifikasikan sama dengan objek referensi. Ciri bentuk diklasifikasikan menggunakan algoritma shape matching. Algoritma shape matching mengukur kemiripan objek berdasarkan jarak antar titik dalam objek geometri. Semakin rendah perbedaannya menunjukkan semakin mirip objek tersebut. Sementara ciri dimensi diklasifikasikan menggunakan perhitungan jumlah pixel pada tiap objek. Jumlah pixel dikalibrasi pada jarak tertentu dari pengkapturan objek oleh kamera. Selain itu, algoritma ini pun didesain untuk dapat mengklasifikasi objek yang tidak masuk kategori dan diklasifikasikan sebagai objek yang rusak (Not Good/NG). Algoritma ini selanjutnya diimplemenasikan dalam sebuah konveyor sebagai mesih pemisah objek yang mempunyai 10 keluaran. Sembilan keluaran untuk objek hasil klasifikasi dan satu keluaran untuk objek dalam kategori NG. Hasil eksperimen menunjukkan sistem dapat mengklasifikasi objek dalam 27 kategori dan 1 kategori NG.Kata Kunci: klasifikasi objek, ciri objek, histogram warna RGB, shape mathing, pemilah objek

In this paper, we designed an application and implemented the robot arm control by hand tracking using the stereo camera. The camera captured and tracked the hand motion and saved the coordinate position or the hand motion position in 3D. Our system was designed to track pitch, yaw and roll motion of the hand. Besides that, the system could also be tracked the hand motion of forwarding and backward motion. The hand tracking data were then saved and processed in our system. By using TCP/IP communication, those data were sent to the arm robot and be transformed become the movement of the arm robot. Our system could move the arm robot by the tracking of the hand motion. The experimental results showed that our system successfully reduces the error of the arm robot motion for each motion such as pitch, yaw and roll motion with the motion error 7.28°, 4.70°, 5,37°, respectively.

The spreading of cafes, restaurant, and food courts in a small market area can create a high-level competitive situation among food serving industries. As customer satisfaction is the main key to reach the glory, making up or keeping up a service or product quality is a critical decision. In this research, we presented a steady and easy way out to solve this problem based on face recognition and smile detection method. We implemented an Adaboost (adaptive boosting) algorithm by Viola-Jones which is the robust algorithm for recognizing the face and detecting a smile. It works completely by cascade classifier step to ensure the object detected is a face. Our system performance attained 96,43% of accuracy in real time condition. It is able to detect a face in a range of 25–100 cm, and it can detect a smile from 25–45 cm in a certain position and conditions.

In recent years, nano satellite has gained popularity among students and young researchers. The reason is that, nano satellite has the ability similar to larger satellite, but in tiny compact size. It is easy to made and can be made using low cost devices. However the main problem in making a nano satellite is in the its communication system. Nano satellite communication system has to be reliable to send information from ground station to nano satellite or vice versa. In this paper, we propose a nano satellite communication system using Raspberry Pi, and a HackRF SDR which is programmed using GNURadio. From the testing process, the text data can be transmitted properly from ground station to nano satellite using GMSK modulation scheme. This communication system also has ability to be reconfigured, which means many modulation scheme and algorithm can be implemented easily without changing the hardware.

This paper proposed a goal detection and opponent avoidance algorithm for robot soccer using color filtering and contour extraction. The paper presented a robust and simple algorithm based on an image captured by robot soccer to recognizing and locating a goal and avoiding from the opponent. The proposed algorithm used a color filtering in the HSV color space to distinguish and detect goal from the background image. The detected goal was then extracted using contour extraction to ensure the detection result. To reduce the noise, the morphology filter was applied to the detected object. The opponent robot was also detected by using HSV color filtering. The opponent robot has a designation color team that is different with our robot team. In order avoiding from opponent robot after detecting its color, we used ping sensor to detect the distance between robots. In the certain distance, our robot could avoid collision with an opponent robot with moving to the left or right side of the opponent robot. The experimental result showed the satisfactory result in detecting goal and avoiding an opponent. The goal successfully was detected from 1.5 m until 8.5 m distance from our robot. The robot successfully avoided the opponent robot in the distance of 40 cm, The robot moved to the right, or left side depended upon the opponent position.

The image processing is not only used to detect and recognize the object. It also can be used to calculate the amount of a buckle object. This paper presented a method which can calculate the amount of a buckle gas cylinder seal. At first, the camera detected a buckle of the seal in real-time. Then, the HSL color space is used to remove background image so that blob counting can detect the seal easily. The pixel of blob counting obtained will be compared to an original pixel in order to build the relation using the polynomial equation to count the seal. By combining the blob counting result, the buckle of the seal can be counted as seen in the experimental results which are done in the real-time application.

Tracking multiple objects is more challenging than tracking a single object. Some problems arise in multiple-object tracking that do not exist in single-object tracking, such as object occlusion, the appearance of a new object and the disappearance of an existing object, updating the occluded object, etc. In this article, we present an approach to handling multiple-object tracking in the presence of occlusions, background clutter, and changing appearance. The occlusion is handled by considering the predicted trajectories of the objects based on a dynamic model and likelihood measures. We also propose target-model-update conditions, ensuring the proper tracking of multiple objects. The proposed method is implemented in a probabilistic framework such as a particle filter in conjunction with a color feature. The particle filter has proven very successful for nonlinear and non-Gaussian estimation problems. It approximates a posterior probability density of the state, such as the object's position, by using samples or particles, where each state is denoted as the hypothetical state of the tracked object and its weight. The observation likelihood of the objects is modeled based on a color histogram. The sample weight is measured based on the Bhattacharya coefficient, which measures the similarity between each sample's histogram and a specified target model. The algorithm can successfully track multiple objects in the presence of occlusion and noise. Experimental results show the effectiveness of our method in tracking multiple objects.

We proposed a method for object tracking employing a particle filter based on color feature method. A histogram‐based framework is used to describe the features. Histograms are useful because they have property that they allow changes in the object appearance while the histograms remain the same. Particle filtering is used because it is very robust for non‐linear and non‐Gaussian dynamic state estimation problems and performs well when clutter and occlusions are present on the image. Bhattacharyya distance is used to weight the samples in the particle filter by comparing each sample’s histogram with a specified target model and it makes the measurement matching and sample’s weight updating more reasonable. The method is capable to track successfully the moving object in different outdoor environment with and without initial positions information, and also, capable to track the moving object in the presence of occlusion using an appearance condition. In this paper, we propose a color features‐based method for object tracking based on the particle filters. The experimental results and data show the feasibility and the effectiveness of our method., International Conference on Power Control and Optimization, 1-3, June 2009, Bali, Indonesia

The increasing interest in the object tracking is motivated by a huge number of promising applications that can now be tackled in real-time applications. These applications include performance analysis, surveillance, video-indexing, smart interfaces, teleconferencing and video compression and so on. However, object tracking can be extremely complex and timeconsuming especially when it is done in outdoor environments. Here, we can mention some problems of object tracking in outdoor environments such as fake-motion background, illumination changes, shadows and presence of clutter. A variety of tracking algorithms have been proposed and implemented to overcome these difficulties. They can be roughly classified into two categories: deterministic methods and stochastic methods. Deterministic methods typically track the object by performing an iterative search for a similarity between the template image and the current one. The algorithms which utilize the deterministic method are background subtraction (Heikkila & Silven, 1999; Stauffer & Grimson, 1999; McIvor, 2000; Liu et al., 2001), inter-frame difference (Lipton et al., 1998; Collins et al., 2000), optical flow (Meyer et al., 1998), skin color extraction (Cho et al., 2001; Phung et al., 2003) and so on. On the other hand, the stochastic methods use the state space to model the underlying dynamics of the tracking system such as Kalman filter (Broida & Chellappa, 1986; Arulampalam et al., 2002) and particle filter (Isard & Black, 1998; Kitagawa, 1996; Gordon et al., 1993; Ristic et al., 2004). Kalman filter is a common approach for dealing with target tracking in the probabilistic framework. In a linear-Gaussian model with linear measurement, there is always only one mode in the posterior probability density function (pdf). The Kalman filter can be used to propagate and update the mean and covariance of the distribution of this model (Arulampalam et al., 2002). But it cannot resolve the tracking problem when the model is nonlinear and non-Gaussian (Tanizaki, 1987). For nonlinear or non-Gaussian problems, it is impossible to evaluate the distributions analytically and many algorithms have been proposed to approximate them. The extended Kalman filter can deal to this problem, but still has a problem when the nonlinearity and non-Gaussian cannot be approximated accurately. To overcome those problems, particle filter has been introduced by many researchers and become popular algorithm to estimate the problem of nonlinear and non-Gaussian estimation framework. The particle filter, also known as sequential Monte Carlo (Kitagawa, 1996), is the most popular approach which recursively constructs the posterior pdf of the state space using Monte Carlo integration. It approximates a posterior probability density of the state such as the object position by using samples or

Object tracking is a challenging problem due to the presence of noise, occlusion, clutter and dynamic change in the scene other than the motion of object of interest. A variety of tracking algorithms has been proposed and implemented to overcome these difficulties, but there are still some problems need to be covered. This paper proposed an algorithm to track the moving objects employing a color-based particle filter considering the single object and multiple objects in outdoor environment. We rely on Bhattacharya distance to measure the similarity between the color distribution of the target model and particles. We propose also a target-model update condition, ensuring the proper tracking object. The method is capable to track successfully the object in different outdoor environment in the presence of occlusion, clutter and dynamic change. Some experimental results and data show the feasibility and the effectiveness of our method.

We proposed a method for automatic detection and tracking of moving object employing a particle filter in conjunction with a color feature method. The particle filtering is used because it is robust for non-linear and non-Gaussian dynamic state estimation problems and performs well when clutter and occlusions are present on the image. A histogram-based framework is used to describe the color feature of the target object. Bhattacharyya distance is used to measure the similarity between each sample's histogram with a specified target model. The target model update is performed to obtain the best match to the target model. The method is capable to detect and track successfully the moving object in different outdoor environment based on variance of the samples and an appearance condition. The experimental results and data show the feasibility and the effectiveness of our method.

In this paper, we propose a method for identification of persons using feature points which are taken from different angle and estimating of face direction using eigenspace technique. The face images are extracted on image sequences which are captured by a camera using image processing techniques. The face directions are estimated based on the eigenspace technique. Furthermore, the locations of face feature points are determined using a separability filter. Finally, the human faces are identified using the statistical features. The feature points for face identification are six points which are obtained the length of eyes, nostrils and angle of mouth. The experiments are performed on real time video image. The satisfactory results are shown along with discussions.

In this paper, we propose a new technique to detect and track the interested moving person employing a block matching technique. The blocks are defined by dividing the image frame into non-overlapping square parts and made in the previous and current frame. The blocks are made based on the peripheral increment sign correlation image. The increment sign of each block is calculated by comparing the pixel value of the neighborhood to the considered pixel. The correlation value between each block in the previous and current frame is calculated to evaluate the matching block. The high correlation value shows that the block is matched. The interested moving object is determined when the number of matching blocks in the previous and current frame is higher than a certain threshold value. Our method is implemented in real time application by using a camera and the satisfied results are achieved.

Automatic detection and tracking of moving object is very important task for security system, monitoring activity and surveillance application. It is, however, still under the developmental stage and needs to be robust performance when applied in an unconstrained environment. Many approaches have been developed to detect motion, namely, optical flow, frame difference, background subtraction and skin color extraction. These methods are sensitive to illumination changes and small movement in the background such as moving leaves of trees that will cause inaccurate detection. Some techniques have been applied to reduce this kind of noise. In this paper we propose a new method by using a low resolution image to reduce that kind of noise so we can get an accurate tracking object.