TY - JOUR
T1 - Vehicle Perception from Satellite
AU - Zhao, Bin
AU - Han, Pengfei
AU - Li, Xuelong
N1 - Publisher Copyright:
© 1979-2012 IEEE.
PY - 2024/4/1
Y1 - 2024/4/1
N2 - Satellites are capable of capturing high-resolution videos. It makes vehicle perception from satellite become possible. Compared to street surveillance, drive recorder or other equipments, satellite videos provide a much broader city-scale view, so that the global dynamic scene of the traffic are captured and displayed. Traffic monitoring from satellite is a new task with great potential applications, including traffic jams prediction, path planning, vehicle dispatching, etc. Practically, limited by the resolution and view, the captured vehicles are very tiny (a few pixels) and move slowly. Worse still, these satellites are in Low Earth Orbit (LEO) to capture such high-resolution videos, so the background is also moving. Under this circumstance, traffic monitoring from the satellite view is an extremely challenging task. To attract more researchers into this field, we build a large-scale benchmark for traffic monitoring from satellite. It supports several tasks, including tiny object detection, counting and density estimation. The dataset is constructed based on 12 satellite videos and 14 synthetic videos recorded from GTA-V. They are separated into 408 video clips, which contain 7,336 real satellite images and 1,960 synthetic images. 128,801 vehicles are annotated totally, and the number of vehicles in each image varies from 0 to 101. Several classic and state-of-the-art approaches in traditional computer vision are evaluated on the datasets, so as to compare the performance of different approaches, analyze the challenges in this task, and discuss the future prospects.
AB - Satellites are capable of capturing high-resolution videos. It makes vehicle perception from satellite become possible. Compared to street surveillance, drive recorder or other equipments, satellite videos provide a much broader city-scale view, so that the global dynamic scene of the traffic are captured and displayed. Traffic monitoring from satellite is a new task with great potential applications, including traffic jams prediction, path planning, vehicle dispatching, etc. Practically, limited by the resolution and view, the captured vehicles are very tiny (a few pixels) and move slowly. Worse still, these satellites are in Low Earth Orbit (LEO) to capture such high-resolution videos, so the background is also moving. Under this circumstance, traffic monitoring from the satellite view is an extremely challenging task. To attract more researchers into this field, we build a large-scale benchmark for traffic monitoring from satellite. It supports several tasks, including tiny object detection, counting and density estimation. The dataset is constructed based on 12 satellite videos and 14 synthetic videos recorded from GTA-V. They are separated into 408 video clips, which contain 7,336 real satellite images and 1,960 synthetic images. 128,801 vehicles are annotated totally, and the number of vehicles in each image varies from 0 to 101. Several classic and state-of-the-art approaches in traditional computer vision are evaluated on the datasets, so as to compare the performance of different approaches, analyze the challenges in this task, and discuss the future prospects.
KW - Density estimation
KW - remote sensing
KW - tiny object detection
KW - vehicle counting
UR - http://www.scopus.com/inward/record.url?scp=85179104811&partnerID=8YFLogxK
U2 - 10.1109/TPAMI.2023.3335953
DO - 10.1109/TPAMI.2023.3335953
M3 - 文章
C2 - 38015706
AN - SCOPUS:85179104811
SN - 0162-8828
VL - 46
SP - 2545
EP - 2554
JO - IEEE Transactions on Pattern Analysis and Machine Intelligence
JF - IEEE Transactions on Pattern Analysis and Machine Intelligence
IS - 4
ER -