Object Tracking and Geo-Localization from Street Images

Wilson, Daniel H.; Alshaabi, Thayer; Oort, Colin Michael Van; Zhang, Xiaohan; Nelson, Jonathan; Wshah, Safwan

doi:10.3390/rs14112575

Cited by 13 publications

(4 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The measurement of the operating speed of public transport within the area of an entire city or distinguished transport zones is performed using GPS tracker data [23,24]. For the purpose of the present study, we used the database of server geoinformation software MicroGIS for public transport in Lviv city (Ukraine).…”

Section: Methodsmentioning

confidence: 99%

Public Transport Prioritization and Descriptive Criteria-Based Urban Sections Classification on Arterial Streets

et al. 2023

View full text Add to dashboard Cite

The present paper is aimed at improving minimization methods in traffic flows, particularly reducing the costs of civil transportation through sections of the transport network by giving priority to public transport in densely developed areas. In cities with a radial and radial–circular planning scheme of the road network, where arterial traffic flows converge in the central part, the challenge of street congestion with traffic often arises. As a result, delays of all types of vehicles increase, which causes excessive travel time for users of private and public transport. In this regard, it is proposed to divide the sections of the transport network into eight types based on their geometric parameters and traffic conditions. This differentiation of sections improves the existing methods for determining the spatial delay of traffic flows on sections of the transport network with different parameters. It was achieved by considering the duration of vehicles passing signalized intersections and pedestrian crosswalks and the sections of streets between them, while simultaneously recording the duration of public transport movement, as well as the time they spend at stopping points, using GPS receivers. The results of onsite monitoring and further computations revealed that there are particular urban sections with specific, different distances between adjacent stop lines that are critical for public transport operation. Furthermore, based on the delay criterion, there were three different passage modes proposed to improve the efficiency of the traffic.

show abstract

Section: Methodsmentioning

confidence: 99%

Public Transport Prioritization and Descriptive Criteria-Based Urban Sections Classification on Arterial Streets

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Visual object tracking, predicting the dynamic state of targets based on initial video frame cues, is fundamental research for applications such as visual surveillance [1], humancomputer interaction [2], and autonomous driving [3,4]. In the Earth observation field, remarkable advancements in video satellite technology [5,6] have been witnessed in recent years.…”

Section: Introductionmentioning

confidence: 99%

Adaptive and Anti-Drift Motion Constraints for Object Tracking in Satellite Videos

Fan,

2024

Remote Sensing

View full text Add to dashboard Cite

Object tracking in satellite videos has garnered significant attention due to its increasing importance. However, several challenging attributes, such as the presence of tiny objects, occlusions, similar objects, and background clutter interference, make it a difficult task. Many recent tracking algorithms have been developed to tackle these challenges in tracking a single interested object, but they still have some limitations in addressing them effectively. This paper introduces a novel correlation filter-based tracker, which uniquely integrates attention-enhanced bounding box regression and motion constraints for improved single-object tracking performance. Initially, we address the regression-related interference issue by implementing a spatial and channel dual-attention mechanism within the search area’s region of interest. This enhancement not only boosts the network’s perception of the target but also improves corner localization. Furthermore, recognizing the limitations in small size and low resolution of target appearance features in satellite videos, we integrate motion features into our model. A long short-term memory (LSTM) network is utilized to create a motion model that can adaptively learn and predict the target’s future trajectory based on its historical movement patterns. To further refine tracking accuracy, especially in complex environments, an anti-drift module incorporating motion constraints is introduced. This module significantly boosts the tracker’s robustness. Experimental evaluations on the SatSOT and SatVideoDT datasets demonstrate that our proposed tracker exhibits significant advantages in satellite video scenes compared to other recent trackers for common scenes or satellite scenes.

show abstract

“…Different from same-view geo-localization which utilizes a geo-tagged ground images database for referencing, CVGL takes aerial images as reference data that is more accessible [9]. CVGL facilitates various tasks such as autonomous driving [10], unmanned aerial vehicle navigation [11], object localization [12], and augmented reality [13] by providing more accurate location estimation under certain environments. Existing approaches typically treat CVGL as an image retrieval problem [9].…”

Section: Introductionmentioning

confidence: 99%

Cross-View Geo-Localization via Learning Disentangled Geometric Layout Correspondence

Zhang

Sultani

et al. 2023

AAAI

Self Cite

View full text Add to dashboard Cite

Cross-view geo-localization aims to estimate the location of a query ground image by matching it to a reference geo-tagged aerial images database. As an extremely challenging task, its difficulties root in the drastic view changes and different capturing time between two views. Despite these difficulties, recent works achieve outstanding progress on cross-view geo-localization benchmarks. However, existing methods still suffer from poor performance on the cross-area benchmarks, in which the training and testing data are captured from two different regions. We attribute this deficiency to the lack of ability to extract the spatial configuration of visual feature layouts and models' overfitting on low-level details from the training set. In this paper, we propose GeoDTR which explicitly disentangles geometric information from raw features and learns the spatial correlations among visual features from aerial and ground pairs with a novel geometric layout extractor module. This module generates a set of geometric layout descriptors, modulating the raw features and producing high-quality latent representations. In addition, we elaborate on two categories of data augmentations, (i) Layout simulation, which varies the spatial configuration while keeping the low-level details intact. (ii) Semantic augmentation, which alters the low-level details and encourages the model to capture spatial configurations. These augmentations help to improve the performance of the cross-view geo-localization models, especially on the cross-area benchmarks. Moreover, we propose a counterfactual-based learning process to benefit the geometric layout extractor in exploring spatial information. Extensive experiments show that GeoDTR not only achieves state-of-the-art results but also significantly boosts the performance on same-area and cross-area benchmarks. Our code can be found at https://gitlab.com/vail-uvm/geodtr.

show abstract

Object Tracking and Geo-Localization from Street Images

Cited by 13 publications

References 44 publications

Public Transport Prioritization and Descriptive Criteria-Based Urban Sections Classification on Arterial Streets

Public Transport Prioritization and Descriptive Criteria-Based Urban Sections Classification on Arterial Streets

Adaptive and Anti-Drift Motion Constraints for Object Tracking in Satellite Videos

Cross-View Geo-Localization via Learning Disentangled Geometric Layout Correspondence

Contact Info

Product

Resources

About