Data Association for Multi-Object Visual Tracking

Betke, Margrit; Wu, Zheng

doi:10.1007/978-3-031-01816-9

Cited by 10 publications

(2 citation statements)

References 199 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, ML with AED outperforms several cyberbullying detection approaches. First, (Betke & Wu, 2017) employed DL models to identify cyberbullying. (A.…”

Section: Discussionmentioning

confidence: 99%

Improving Cyberbullying Detection Through Adaptive External Dictionary in Machine Learning

Qudah,

Alhija,

Tarawneh

2023

Preprint

View full text Add to dashboard Cite

Cyberbullying has escalated due to social media's rapid growth, endangering internet security. Correct these harmful habits. ML is used to research cyberbullying on Twitter. This model is enhanced with adaptive external dictionary (AED). Terms that are negative and positive are produced manually. The dynamic lists of positive and negative words produced by AED sentiment analysis. The dataset has positive and negative tweet columns. Social media's fast expansion has increased cyberbullying, threatening online safety. Recognizing and addressing these risky activities quickly requires a comprehensive system. Uses ML to detect Twitter cyberbullying (ML). This model detects better using Adaptive External Dictionary.47K Kaggle tweets made the AED. Manual refinement only produces negative and positive phrases in the first portion, relevant to our topic. AED sentiment analysis creates dynamic lists of Positive Words (PW) and Negative Words (NW) in this study. Tweets are columns. Combining internet data with positive and negative word counts identifies cyberbullying.

show abstract

“…Thus, ML with AED outperforms several cyberbullying detection approaches. First, (Betke & Wu, 2017) employed DL models to identify cyberbullying. (A.…”

Section: Discussionmentioning

confidence: 99%

Improving Cyberbullying Detection Through Adaptive External Dictionary in Machine Learning

Qudah,

Alhija,

Tarawneh

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…To better understand the detection process and the results achieved by this study, detection assessment measurements were used to quantify the performance of our detection algorithm in various situations. Among the popular measures for reporting results, there are basic concepts and evaluation criteria used for object detection [ 51 ] as follows: Confidence level: object detection model output score linked to the bounding of the object detected. Intersection over union IoU: the ratio of the area of overlap between the predicted bounding box and the ground truth bounding box to the area of union between the two boxes.…”

Section: Assessment Of the Different Network Architectures Implementedmentioning

confidence: 99%

3D Object Detection for Self-Driving Cars Using Video and LiDAR: An Ablation Study

Salmane

Velázquez

Khoudour

et al. 2023

Sensors

View full text Add to dashboard Cite

Methods based on 64-beam LiDAR can provide very precise 3D object detection. However, highly accurate LiDAR sensors are extremely costly: a 64-beam model can cost approximately USD 75,000. We previously proposed SLS–Fusion (sparse LiDAR and stereo fusion) to fuse low-cost four-beam LiDAR with stereo cameras that outperform most advanced stereo–LiDAR fusion methods. In this paper, and according to the number of LiDAR beams used, we analyzed how the stereo and LiDAR sensors contributed to the performance of the SLS–Fusion model for 3D object detection. Data coming from the stereo camera play a significant role in the fusion model. However, it is necessary to quantify this contribution and identify the variations in such a contribution with respect to the number of LiDAR beams used inside the model. Thus, to evaluate the roles of the parts of the SLS–Fusion network that represent LiDAR and stereo camera architectures, we propose dividing the model into two independent decoder networks. The results of this study show that—starting from four beams—increasing the number of LiDAR beams has no significant impact on the SLS–Fusion performance. The presented results can guide the design decisions by practitioners.

show abstract

Depth-Aware Multi-object Tracking in Spherical Videos

Presti

Mazzola

Averna

et al. 2022

Image Analysis and Processing – ICIAP 2022

View full text Add to dashboard Cite

This paper deals with the multi-object tracking (MOT) problem in videos acquired by 360-degree cameras. Targets are tracked by a frame-by-frame association strategy. At each frame, candidate targets are detected by a pre-trained state-of-the-art deep model. Associations to the targets known till the previous frame are found by solving a data association problem considering the locations of the targets in the scene. In case of a missing detection, a Kalman filter is used to track the target. Differently than works at the state-of-the-art, the proposed tracker considers the depth of the targets in the scene. The distance of the targets from the camera can be estimated by geometrical facts peculiar to the adopted 360-degree camera and by assuming targets move on the groundplane. Distance estimates are used to model the location of the targets in the scene, solve the data association problem, and handle missing detection. Experimental results on publicly available data demonstrate the effectiveness of the adopted approach.

show abstract

Data Association for Multi-Object Visual Tracking

Cited by 10 publications

References 199 publications

Improving Cyberbullying Detection Through Adaptive External Dictionary in Machine Learning

Improving Cyberbullying Detection Through Adaptive External Dictionary in Machine Learning

3D Object Detection for Self-Driving Cars Using Video and LiDAR: An Ablation Study

Depth-Aware Multi-object Tracking in Spherical Videos

Contact Info

Product

Resources

About