Multiple Object Tracking Using Edge Multi-Channel Gradient Model With ORB Feature

Chen, Jieyu; Xi, Zhenghao; Chi, Wei; Lu, Junxin; Niu, Yuhui; Li, Zhongfeng

doi:10.1109/access.2020.3046763

Cited by 18 publications

(6 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Others have investigated methods to handle occlusion and track-ID switch cases, such as multi-object tracking algorithms that incorporate temporal information and appearance-based models for re-identification [ 19 ]. However, despite the progress made in cattle tracking research [ 20 ], there is still a need for more robust and efficient tracking systems that can effectively handle occlusion conditions and track-ID increment cases for miss detection [ 21 ]. The existing literature lacks comprehensive evaluations of different tracking algorithms [ 22 ] specifically tailored for cattle tracking.…”

Section: Research Background and Related Workmentioning

confidence: 99%

Customized Tracking Algorithm for Robust Cattle Detection and Tracking in Occlusion Environments

Mg,

Tin,

Aikawa

et al. 2024

Sensors

View full text Add to dashboard Cite

Ensuring precise calving time prediction necessitates the adoption of an automatic and precisely accurate cattle tracking system. Nowadays, cattle tracking can be challenging due to the complexity of their environment and the potential for missed or false detections. Most existing deep-learning tracking algorithms face challenges when dealing with track-ID switch cases caused by cattle occlusion. To address these concerns, the proposed research endeavors to create an automatic cattle detection and tracking system by leveraging the remarkable capabilities of Detectron2 while embedding tailored modifications to make it even more effective and efficient for a variety of applications. Additionally, the study conducts a comprehensive comparison of eight distinct deep-learning tracking algorithms, with the objective of identifying the most optimal algorithm for achieving precise and efficient individual cattle tracking. This research focuses on tackling occlusion conditions and track-ID increment cases for miss detection. Through a comparison of various tracking algorithms, we discovered that Detectron2, coupled with our customized tracking algorithm (CTA), achieves 99% in detecting and tracking individual cows for handling occlusion challenges. Our algorithm stands out by successfully overcoming the challenges of miss detection and occlusion problems, making it highly reliable even during extended periods in a crowded calving pen.

show abstract

Section: Research Background and Related Workmentioning

confidence: 99%

Customized Tracking Algorithm for Robust Cattle Detection and Tracking in Occlusion Environments

Mg,

Tin,

Aikawa

et al. 2024

Sensors

View full text Add to dashboard Cite

show abstract

“…Other tracking by-detection methods include Chen et al [60] that suggested the MOTDT, which employs a scoring mechanism based entirely on convolutional neural networks to choose candidates optimally. Euclidean distances between the retrieved object appearance features were applied to enhance the association phase further.…”

Section: Tracking By Detectionmentioning

confidence: 99%

Improved DeepSORT-Based Object Tracking in Foggy Weather for AVs Using Sematic Labels and Fused Appearance Feature Network

Ogunrinde¹,

Bernadin²

2023

Preprint

View full text Add to dashboard Cite

The presence of fog in the background can prevent small and distant objects from being detected, let alone tracked. Under safety-critical conditions, multi-object tracking models require faster-tracking speed while maintaining high object-tracking accuracy. The original DeepSORT algorithm used YOLOv4 for the detection phase, and a simple neural network for deep appearance descriptor. Consequently, the feature map generated loses relevant details about the track being matched with a given detection in fog. Targets with a high degree of appearance similarity on the detection frame are more likely to be mismatched, resulting in identity switches or track failures in heavy fog. We propose an improved multi-object tracking model based on the DeepSORT algorithm to im-prove tracking accuracy and speed under foggy weather conditions. First, we employed our camera-radar fusion network (CR-YOLOnet) in the detection phase for faster and more accurate object detection. We proposed an appearance feature network to replace the basic convolutional neural network. We incorporated GhostNet to take the place of the traditional convolutional layers to generate more features and reduce computational complexities and cost. We adopted a segmentation module and fed the semantic labels of the corresponding input frame to add rich semantic information to the low-level appearance feature maps. Our proposed method outperformed YOLOv5 + DeepSORT with a 35.15% increase in multi-object tracking accuracy, a 32.65% increase in multi-object tracking precision, the speed increased by 37.56%, and identity switches decreased by 46.81%.

show abstract

“…Opencv memiliki lebih dari 47 ribu orang pengguna komunitas dan perkiraan jumlah unduhan melebihi 18 juta. Perpustakaan digunakan secara luas di perusahaan, kelompok penelitian dan oleh badan pemerintah [7].…”

Section: Gambar 1 Contoh Penerapan Computer Vision Opencvunclassified

Object Tracking Berbasis Keypoint Menggunakan Algoritma Orb (Oriented Fast and Rotated Brief) Pada Raspberry Pi

Saraswati,

2023

IRIS

View full text Add to dashboard Cite

Perkembangan teknologi saat ini, penggunaan gambar digital sudah menjadi kebutuhan untuk berbagai keperluan. Citra digital berperan untuk memberikan informasi tentang apa yang ada pada suatu gambar digital. Object tracking merupakan salah satu penelitian yang menarik dalam computer vision dalam pencitraan digital. Object tracking digunakan melalui beberapa metode, salah satunya menggunakan keypoint dengan algoritma ORB sebagai dasarnya. Algoritma ORB memiliki kecepatan yang sangat tinggi, akan tetapi apakah bisa dijalankan di Raspberry Pi. bagaimana unjuk kerja algoritma tersebut bila dibandingkan dengan algoritma SIFT dan SURF. Setelah dilakukan pengujian, dihasilkan bahwa untuk unjuk kerja algoritma ORB lebih cepat dibandingkan dengan algoritma SURF dan SIFT. Kekurangan dari algoritma tersebut masih banyak kehilangan keypoint, masih terpengaruh dengan lingkungan sekitar objek, serta Raspberry Pi yang belum bisa secara maksimal untuk digunakan sebagai object tracking.

show abstract

Multiple Object Tracking Using Edge Multi-Channel Gradient Model With ORB Feature

Cited by 18 publications

References 47 publications

Customized Tracking Algorithm for Robust Cattle Detection and Tracking in Occlusion Environments

Customized Tracking Algorithm for Robust Cattle Detection and Tracking in Occlusion Environments

Improved DeepSORT-Based Object Tracking in Foggy Weather for AVs Using Sematic Labels and Fused Appearance Feature Network

Object Tracking Berbasis Keypoint Menggunakan Algoritma Orb (Oriented Fast and Rotated Brief) Pada Raspberry Pi

Contact Info

Product

Resources

About