1. |
- Kristan, Matej, et al.
(författare)
-
The first visual object tracking segmentation VOTS2023 challenge results
- 2023
-
Ingår i: 2023 IEEE/CVF International conference on computer vision workshops (ICCVW). - : Institute of Electrical and Electronics Engineers Inc.. - 9798350307443 - 9798350307450 ; , s. 1788-1810
-
Konferensbidrag (refereegranskat)abstract
- The Visual Object Tracking Segmentation VOTS2023 challenge is the eleventh annual tracker benchmarking activity of the VOT initiative. This challenge is the first to merge short-term and long-term as well as single-target and multiple-target tracking with segmentation masks as the only target location specification. A new dataset was created; the ground truth has been withheld to prevent overfitting. New performance measures and evaluation protocols have been created along with a new toolkit and an evaluation server. Results of the presented 47 trackers indicate that modern tracking frameworks are well-suited to deal with convergence of short-term and long-term tracking and that multiple and single target tracking can be considered a single problem. A leaderboard, with participating trackers details, the source code, the datasets, and the evaluation kit are publicly available at the challenge website1
|
|
2. |
- Zhang, Pengcheng, et al.
(författare)
-
Geospatial learning for large-scale transport infrastructure depth prediction
- 2024
-
Ingår i: International Journal of Applied Earth Observation and Geoinformation. - : Elsevier. - 1569-8432 .- 1872-826X. ; 132
-
Tidskriftsartikel (refereegranskat)abstract
- Transportation infrastructure supports the smooth mobility of humans, commodities, and services. Pavement depth measures the quality of road infrastructure through representing the thickness of road surfaces, and influences various aspects of construction projects. However, accurately modeling and predicting pavement depth has been a critical challenge due to diverse and complex factors, such as weather dynamics, traffic patterns, maintenance interventions, and environmental fluctuations. This study develops a second-dimension spatial learning (SDSL) model that integrates geospatial models and machine learning for large-scale pavement depth prediction. SDSL models are implemented in pavement prediction for eight distinct regions in Western Australia, and they are validated using the observation of pavement depth through cross-validation. Results demonstrate that the proposed SDSL models can more accurately predict large-scale pavement depth than the existing first-dimension spatial learning (FDSL) models, with 17.3% to 37.6% increase of R2 values, 1.46% to 16.5% reduction of RMSE, 1.7% to 31.1% reduction of MAE and 21.0% reduction of prediction uncertainty. SDSL models enhance effective infrastructure management by accurately predicting pavement depth, essential for maintaining large-scale transportation infrastructure. The study significantly contributes to the efficient management of sustainable infrastructure assets, saving time and money. © 2024 The Authors
|
|