Similarity based person re-identification for multi-object tracking using deep Siamese network

Suljagic, Harun; Bayraktar, Ertuğrul; Çelebi, Numan

doi:10.1007/s00521-022-07456-2

Cited by 24 publications

(9 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ByteTrack [28], GSDT [29], RSOADL-MODT [30], CGTracker [31], Hybrid motion model [33], FlowNet2-DL [34], and SAT [36]. When compared with the existing methods, the proposed ResNet50-DAN achieves better MOTA of 84.2%, IDF1 of 80.3%, FP of 10352, and ID-Sw of 1284 respectively.…”

Section: 3comparative Analysismentioning

confidence: 98%

See 1 more Smart Citation

ResNet50-deep affinity network for object detection and tracking in videos

2024

IJATEE

View full text Add to dashboard Cite

Multiple-object tracking (MOT) plays a crucial role in addressing many fundamental challenges within the fields of computer vision and video analysis. The majority of MOT methods rely on two primary processes: object detection and data association. Initially, each video frame is analyzed to detect objects, followed by a subsequent step that establishes correlations among the detected objects across multiple frames to generate their tracks. However, the data association for tracking often relies on manually defined criteria such as motion, appearance, grouping, and spatial proximity, among others. In the study, the ResNet50-deep affinity network (DAN) was introduced, which had been designed for the detection and tracking of objects in videos, including those that appear and disappear between frames. The proposed method was evaluated using the widely recognized MOT17 dataset to address MOT challenges. During the preprocessing phase, photometric distortion correction, frame expansion, and cropping were performed. The ResNet50 model was utilized to extract features. The DAN was employed to identify object appearances in video frames and to calculate their cross-frame affinities (CFA). The approach was compared with existing research, including DAN, ByteTrack, the graph neural network for simultaneous detection and tracking (GSDT), the reptile search optimization algorithm with deep learning-based multiple object detection and tracking (RSOADL-MODT), the center graph network (CGTracker), the hybrid motion model, FlowNet2-deep learning, and the super chained tracker (SCT), to validate the efficiency of theResNet50-DAN method. The ResNet50-DAN method achieved superior results, with a multiple-object tracking accuracy (MOTA) of 84.2%, an F1 score for identification metrics (IDF1) of 80.3%, 10,352 false positives (FP), and 1,284 identity switches (ID-Sw). The ResNet50-DAN method demonstrated higher MOTA compared to the existing approaches, including DAN, ByteTrack, GSDT, RSOADL-MODT, CGTracker, the hybrid motion model, FlowNet2-DL, and SCT.

show abstract

Section: 3comparative Analysismentioning

confidence: 98%

“…Suljagic et al [36] implemented a similarity-based person re-id framework (SAT) utilizing a siamese neural network (SNN) for MOT by sharing weights.…”

Section: Literature Surveymentioning

confidence: 99%

ResNet50-deep affinity network for object detection and tracking in videos

2024

IJATEE

View full text Add to dashboard Cite

show abstract

“…Common object detection networks encompass R-CNN [ 13 ], Mask-RCNN [ 14 ], YoLov1~YoLov7 [ 15 , 16 ], Fast re-OBJ [ 17 ], CenterNet [ 18 ], or Siamese network [ 19 ]. For example, Suljagic, H. and Bayraktar, E. et al [ 19 ] innovatively proposed a similarity-based person re-id framework with higher accuracy, fewer ID switches, and false positive and negative rates, called SAT. Altman, L.E.…”

Section: Introductionmentioning

confidence: 99%

Real-Time 3D Tracking of Multi-Particle in the Wide-Field Illumination Based on Deep Learning

Luo,

Zhang,

Tan

et al. 2024

Sensors

View full text Add to dashboard Cite

In diverse realms of research, such as holographic optical tweezer mechanical measurements, colloidal particle motion state examinations, cell tracking, and drug delivery, the localization and analysis of particle motion command paramount significance. Algorithms ranging from conventional numerical methods to advanced deep-learning networks mark substantial strides in the sphere of particle orientation analysis. However, the need for datasets has hindered the application of deep learning in particle tracking. In this work, we elucidated an efficacious methodology pivoted toward generating synthetic datasets conducive to this domain that resonates with robustness and precision when applied to real-world data of tracking 3D particles. We developed a 3D real-time particle positioning network based on the CenterNet network. After conducting experiments, our network has achieved a horizontal positioning error of 0.0478 μm and a z-axis positioning error of 0.1990 μm. It shows the capability to handle real-time tracking of particles, diverse in dimensions, near the focal plane with high precision. In addition, we have rendered all datasets cultivated during this investigation accessible.

show abstract

“…The performance of the traditional deep learning(DL) technique relies heavily on collecting a large amount of user data as a prerequisite, especially assuming that the represented data distribution is relatively stationary without dynamic changes. Towards robust and efficient model retraining, we utilize a one-shot learning approach based on the Siamese network [ 27 , 28 , 29 ], with two core techniques: first component reverse (FCR) extraction and convolution block attention module (CBAM), achieving high model robustness and performance in heterogeneous scenarios (e.g., identifying unseen users). A unique velocity distribution profiling (VDP) is calculated from a double-source interference pattern, reflecting the personal motion features.…”

Section: Introductionmentioning

confidence: 99%

MeshID: Few-Shot Finger Gesture Based User Identification Using Orthogonal Signal Interference

Zheng,

Zhang,

Jiang

et al. 2024

Sensors

View full text Add to dashboard Cite

Radio frequency (RF) technology has been applied to enable advanced behavioral sensing in human-computer interaction. Due to its device-free sensing capability and wide availability on Internet of Things devices. Enabling finger gesture-based identification with high accuracy can be challenging due to low RF signal resolution and user heterogeneity. In this paper, we propose MeshID, a novel RF-based user identification scheme that enables identification through finger gestures with high accuracy. MeshID significantly improves the sensing sensitivity on RF signal interference, and hence is able to extract subtle individual biometrics through velocity distribution profiling (VDP) features from less-distinct finger motions such as drawing digits in the air. We design an efficient few-shot model retraining framework based on first component reverse module, achieving high model robustness and performance in a complex environment. We conduct comprehensive real-world experiments and the results show that MeshID achieves a user identification accuracy of 95.17% on average in three indoor environments. The results indicate that MeshID outperforms the state-of-the-art in identification performance with less cost.

show abstract

Similarity based person re-identification for multi-object tracking using deep Siamese network

Cited by 24 publications

References 57 publications

ResNet50-deep affinity network for object detection and tracking in videos

ResNet50-deep affinity network for object detection and tracking in videos

Real-Time 3D Tracking of Multi-Particle in the Wide-Field Illumination Based on Deep Learning

MeshID: Few-Shot Finger Gesture Based User Identification Using Orthogonal Signal Interference

Contact Info

Product

Resources

About