Implementation of Depth-HOG based Human Upper Body Detection On A Mini PC Using A Low Cost Stereo Camera

Dewantara, Bima Sena Bayu; Ardilla, Fernando; Thoriqy, Ardiansyah At

doi:10.1109/icaiit.2019.8834580

Cited by 10 publications

(7 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The real implementation is executed by enabling detection for 60 seconds and replacing it with a different object. Table 3 shows the offline trial of trash detection using previous research method [3] and then Table 4 shows the offline trial of target detection using previous research [4]. Then, Table 5 and Table 6 shows offline trial trash and target detection using our method.…”

Section: Resultsmentioning

confidence: 99%

“…The working of this system is that when the robot successfully detects a trash object, the camera installed on the robot will perform the second function, namely looking for human targets that have the potential to help the robot put trash into the trash bin provided above the robot. Human detection is carried out on the upper part of the human body based on shape features using the HOG and SVM methods [4]. When someone is detected, the robot will make a sound to invite the person to take and put the garbage in the trash bin.…”

Section: B Human Target Detection and Social Persuasivementioning

confidence: 99%

“…Then, the human target and persuasive social interaction was carried out by Dewantara et.al. [4] which achieves 71% of detection results with 4.26 fps. For robot monitoring and communication with the officer, Kisron et.al.…”

mentioning

confidence: 96%

“…Dewantara et.al. [4] proposed Depth-HOG as the shape feature of a human upper body that is classified using SVM to distinguish human or not human. The system was also developed under standard C++ programming on Windows OS platform without any optimization techniques.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Improved Performance of Trash Detection and Human Target Detection Systems using Robot Operating System (ROS)

Kisron

Dewantara

Oktavianto

2021

JRE

Self Cite

View full text Add to dashboard Cite

In a visual-based real detection system using computer vision, the most important thing that must be considered is the computation time. In general, a detection system has a heavy algorithm that puts a strain on the performance of a computer system, especially if the computer has to handle two or more different detection processes. This paper presents an effort to improve the performance of the trash detection system and the target partner detection system of a trash bin robot with social interaction capabilities. The trash detection system uses a combination of the Haar Cascade algorithm, Histogram of Oriented Gradient (HOG) and Gray-Level Coocurrence Matrix (GLCM). Meanwhile, the target partner detection system uses a combination of Depth and Histogram of Oriented Gradient (HOG) algorithms. Robotic Operating System (ROS) is used to make each system in separate modules which aim to utilize all available computer system resources while reducing computation time. As a result, the performance obtained by using the ROS platform is a trash detection system capable of running at a speed of 7.003 fps. Meanwhile, the human target detection system is capable of running at a speed of 8,515 fps. In line with the increase in fps, the accuracy also increases to 77%, precision increases to 87,80%, recall increases to 82,75%, and F1-score increases to 85,20% in trash detection, and the human target detection system has also improved accuracy to 81%, %, precision increases to 91,46%, recall increases to 86,20%, and F1-score increases to 88,42%.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: B Human Target Detection and Social Persuasivementioning

confidence: 99%

mentioning

confidence: 96%

mentioning

confidence: 99%

See 2 more Smart Citations

Improved Performance of Trash Detection and Human Target Detection Systems using Robot Operating System (ROS)

Kisron

Dewantara

Oktavianto

2021

JRE

Self Cite

View full text Add to dashboard Cite

show abstract

“…Secara umum, skema pelacakan menggunakan kamera tunggal atau multi meliputi dua bagian sistem. Pertama, sistem deteksi dimana perlu adanya klasifikasi objek untuk mengenali objek pada suatu urutan gambar dan kedua adalah proses pelacakan posisi objek (Imanuddin, Kristalina, & Dewantara, 2019) (Ardiyanto & Miura, 2014) (Dewantara, Ardilla, & Thoriqy, 2019) berdasarkan sistem deteksi. Tidak jarang pelacakan dengan kamera dikombinasikan dengan teknik handoff dalam pelacakan target yang spesifik.…”

Section: Pendahuluanunclassified

Skema Handover pada Multi-kamera dengan Logika Fuzzy untuk Sistem Pemantauan Orang

2021

Self Cite

View full text Add to dashboard Cite

ABSTRAKAdanya berbagai peristiwa yang membahayakan di tempat keramaian menyebabkan diperlukannya sebuah sistem pemantauan aktifitas manusia di sekitarnya untuk pengawasan keamanan. Sistem multi-kamera sangat cocok digunakan untuk pemantauan target pada lingkungan area yang luas. Disaat target meninggalkan jangkauan area kamera menuju lainnya, proses pemantauan target harus tetap bekerja dan diserahkan ke kamera lainnya. Protokol serah terima target dapat berjalan jika terdapat komunikasi antar kamera yang tersedia. Penelitian ini menyajikan skema handover pada sistem multi-kamera dengan menerapkan pengambilan keputusan handover berbasis logika fuzzy. Dengan begitu, target akan selalu ditangani oleh kamera meskipun target bergerak menjauhinya. Berdasarkan hasil simulasi, skema handover ini mampu mereduksi total number of handover sebesar 20% dibandingkan dengan metode AHCS (Active Handover Control Scheme). Selain itu, handover delay pada metode usulan memperoleh waktu 123.72μs dan masih lebih lama dari AHCS.Kata kunci: handover, multi-kamera, pemantauan orang, fuzzy logic ABSTRACTThe existence of various dangerous events in a crowded place causes the need of surveillance system to monitor the human activity continuously in a certain area. Multi-camera systems are used to monitor targets in large areas. When the target leaves the camera’s range for another, the target monitoring process should continue to work and be left to other cameras. The target handover protocol may work if there is communication between the available cameras. This document presents a handover scheme in a multi-camera system by applying a fuzzy logic handover decision. Thus, the target will always be processed by the camera, even if the target is moving away from it. Based on the simulation results, this handover scheme is able to reduce the total number of handovers by 20% compared to the AHCS (Active Handover Control Scheme) method. In addition, the handover delay in the proposed method obtains 123.72 μs and is still longer than the AHCS.Keywords: handover, multi-camera, human monitoring, fuzzy logic

show abstract

Real-Time Human Intrusion Detection for Home Surveillance Based on IOT

Gaddipati

Krishnaja

Gopan

et al. 2020

Smart Innovation, Systems and Technologies

View full text Add to dashboard Cite

Implementation of Depth-HOG based Human Upper Body Detection On A Mini PC Using A Low Cost Stereo Camera

Cited by 10 publications

References 10 publications

Improved Performance of Trash Detection and Human Target Detection Systems using Robot Operating System (ROS)

Improved Performance of Trash Detection and Human Target Detection Systems using Robot Operating System (ROS)

Skema Handover pada Multi-kamera dengan Logika Fuzzy untuk Sistem Pemantauan Orang

Real-Time Human Intrusion Detection for Home Surveillance Based on IOT

Contact Info

Product

Resources

About