High-Speed tracking-by-detection without using image information

By Erik Bochinski, Volker Eiselein, Thomas Sikora. Advanced Video and Signal Based Surveillance, 2017

676 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Biomedical Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/9f394da08dc44501cc19bc9d2183ecba0d01c46d

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Biomedical Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

FairMOT: On the Fairness of Detection and Re-identification in Multiple Object Tracking (2020, methodology): “IOU-Tracker (Bochinski et al. 2017) directly computes the overlap between the”
Quasi-Dense Similarity Learning for Multiple Object Tracking (2020, background): “Location and motion in MOT The spatial proximity has been proven effective to associate objects in consecutive frames [4, 5].”
UA-DETRAC: A new benchmark and protocol for multi-object detection and tracking (2015, methodology): “14 We evaluate the complete MOT systems constructed from com15 binations of ten object tracking schemes (Andriyenko and Schindler, 16 2011; Pirsiavash et al., 2011; Andriyenko et al., 2012; Dicle et al., 17 2013; Wen et al., 2014; Bae and Yoon, 2014; Geiger et al., 2014; 18 Kim et al., 2015; Bochins”
EasyCom: An Augmented Reality Dataset to Support Algorithms for Easy Communication in Noisy Environments (2021, methodology): “As a remedy, we use an intersection-over-union (IoU) -based tracker [13] to group the detected faces into tracklets and perform the annotation on the tracklet level.”
HOTA: A Higher Order Metric for Evaluating Multi-object Tracking (2020, methodology): “We evaluate 37 different trackers [11,76,7,64,51,84,89,33, 16,82,30,47,15,35,42,85,26,29,17,34,46,41,70,25,31,2, 62,63,9,10,3,69,4,22,37,5] on MOT17 [54].”
Online Multi-Object Tracking with Dual Matching Attention Networks (2018, neutral): “Offline IOU [5] 45.”
Video Instance Segmentation (2019, result): “DeepSORT improves IoUTracker+ on both the IoU matching and using visual similarity, and thus achieves better results.”
The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking (2018, methodology): “Therefore, we evaluate 8 recent algorithms including online methods (CMOT [2], MDP [50], SORT [6] and DSORT [48]) and batch based methods (GOG [35], CEM [30], SMOT [13] and IOUT [7]).”
Spatial-Temporal Relation Networks for Multi-Object Tracking (2019, methodology): “tance, location/motion priors to compute the ﬁnal similarities. The utilization of location/motion features is common as well. Most existing methods assume a prior motion model, such as slow velocity [5] and linear/non-linear motion model [63]. For example, the IoU trackers [5] rely on the assumptio”
Video Instance Segmentation Tracking With a Modified VAE Architecture (2020, methodology): “Mask R-CNN+IT denotes a basic baseline of linking MaskR-CNN output masks by IoU matching with IoUTracker [6].”
BoT-SORT: Robust Associations Multi-Pedestrian Tracking (2022, methodology): “Currently, tracking-by-detection has become the most effective paradigm for the MOT task [54, 3, 48, 4, 58].”
Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Tracking (2020, methodology): “Then, the generated box pairs belonging to the adjacent frame pairs could be associated using simple methods like IoU (Intersection over Union) matching [2] according to their boxes in the common frame.”
Deep Affinity Network for Multiple Object Tracking (2018, background): “[61] leveraged the intersection-over-union and predefined thresholds for the association of objects in frames.”
Rethinking the Competition Between Detection and ReID in Multiobject Tracking (2020, methodology): “In particular, these trackers [2]–[5], [12], [13] divide MOT into two separate tasks, i.”
INTERACTION Dataset: An INTERnational, Adversarial and Cooperative moTION Dataset in Interactive Driving Scenarios with Semantic Maps (2019, methodology): “• Data association: Detections are grouped into tracks using a combination of an Intersection-over-Union [30] tracker which associates detections with high mask overlap in successive frames, and a visual tracker [31] to compensate for miss detections.”