.png){kind=icon}
Return
An improved deep learning architecture for multi-object tracking systems
.png){kind=icon}
PRE
AI
DOI：10.3233/ICA-230702.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Robust and reliable 3D multi-object tracking (MOT) is essential for autonomous driving in crowded urban road scenes. In those scenarios, accurate data association between tracked objects and incoming new detections is crucial. This paper presents a tracking system based on the Kalman filter that uses a deep learning approach to the association problem. The proposed architecture consists of three neural networks. First, a convolutional LSTM network extracts spatiotemporal features from a sequence of detections of the same track. Then, a Siamese network calculates the degree of similarity between all tracks and the new detections found at each new frame. Finally, a recurrent LSTM network is used to extract 3D and bounding box information. This model follows the tracking-by-detection paradigm and has been trained with track sequences to be able to handle missed observations and to reduce identity switches. A validation test was carried out on the Argoverse dataset to validate the performance of the proposed system. The developed deep learning approach could improve current multi-object tracking systems based on classic algorithms like the Kalman filter.
Keywords:
Multi-object tracking
deep learning
Kalman filter
convolutional neural network
data association
Journal
I
IF:
5.3
Papers:
491
Citations:
735
Organization
Cited Papers
ShareSaveCommentary: It's not all means and genes--socio-economic position, variation and genetic confounding
OAAI
OAAIShareSaveDeep learning techniques for recommender systems based on collaborative filtering.png)
EXPERT SYSTEMS
EXPERT SYSTEMSIF2.3
PREAI
ShareSaveShareSave
View more