Detecting Moving Trucks on Roads Using Sentinel-2 Data

Abstract

In most countries, freight is predominantly transported by road cargo trucks. We present a new satellite remote sensing method for detecting moving trucks on roads using Sentinel-2 data. The method exploits a temporal sensing offset of the Sentinel-2 multispectral instrument, causing spatially and spectrally distorted signatures of moving objects. A random forest classifier was trained (overall accuracy: 84%) on visual-near-infrared-spectra of 2500 globally labelled targets. Based on the classification, the target objects were extracted using a developed recursive neighbourhood search. The speed and the heading of the objects were approximated. Detections were validated by employing 350 globally labelled target boxes (mean F1 score: 0.74). The lowest F1 score was achieved in Kenya (0.36), the highest in Poland (0.88). Furthermore, validated at 26 traffic count stations in Germany on in sum 390 dates, the truck detections correlate spatio-temporally with station figures (Pearson r-value: 0.82, RMSE: 43.7). Absolute counts were underestimated on 81% of the dates. The detection performance may differ by season and road condition. Hence, the method is only suitable for approximating the relative truck traffic abundance rather than providing accurate absolute counts. However, existing road cargo monitoring methods that rely on traffic count stations or very high resolution remote sensing data have limited global availability. The proposed moving truck detection method could fill this gap, particularly where other information on road cargo traffic are sparse by employing globally and freely available Sentinel-2 data. It is inferior to the accuracy and the temporal detail of station counts, but superior in terms of spatial coverage.

Transboundary flows in the metacoupled Anthropocene: typology, methods, and governance for global sustainability

“…AIS is an automatic tracking system that uses transceivers on ships (Kapsar et al 2022b), which can provide rich and real-time ship locations and movement trajectories (Mou et al 2020). In addition, remotely sensed satellite imagery can also be used to detect and classify container ships and cargo trucks (Fisser et al 2022, Polinov et al 2022, Shao et al 2023. In combination with auxiliary data, both AIS and remote sensing-derived data can also be used for modeling shipping activities and estimating freight flows.…”

Utilizing Probabilistic Maps and Unscented-Kalman-Filtering-Based Sensor Fusion for Real-Time Monte Carlo Localization

“…The predicted sigma point ( Xk+1 ) for the next time step is calculated using Equation (2), utilizing the object's model given by Equation (9). Then, the predicted state mean vector ( xk+1 ) and its covariance matrix ( Pk+1 ) is calculated by applying Equation (3).…”

“…The technological challenges that need to be solved to attain complete autonomy are divided into four areas by designers and researchers in the autonomous driving field: perception, localization, path planning, and controls [1]. Perception is concerned with the task of detecting where objects like cars [2], trucks [3], bikes [4], and pedestrians are [5]; which lane the egocar is driving in [6]; where its boundaries are [7]; and so on. The solutions to these perception subtasks are researched using machine learning techniques that co-ordinate various sensors to accurately detect the surroundings of the egocar [8].…”