Deep Vehicle Detection in Satellite Video
- URL: http://arxiv.org/abs/2204.06828v1
- Date: Thu, 14 Apr 2022 08:54:44 GMT
- Title: Deep Vehicle Detection in Satellite Video
- Authors: Roman Pflugfelder and Axel Weissenfeld and Julian Wagner
- Abstract summary: Vehicle detection is perhaps impossible in single satellite images due to the tininess of vehicles (4 pixel) and their similarity to the background EO.
A new model of a compact $3 times 3$ neural network is proposed which neglects pooling layers and uses leaky ReLUs.
Empirical results on two new annotated satellite videos reconfirm the applicability of this approach for vehicle detection.
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: This work presents a deep learning approach for vehicle detection in
satellite video. Vehicle detection is perhaps impossible in single EO satellite
images due to the tininess of vehicles (4-10 pixel) and their similarity to the
background. Instead, we consider satellite video which overcomes the lack of
spatial information by temporal consistency of vehicle movement. A new
spatiotemporal model of a compact $3 \times 3$ convolutional, neural network is
proposed which neglects pooling layers and uses leaky ReLUs. Then we use a
reformulation of the output heatmap including Non-Maximum-Suppression (NMS) for
the final segmentation. Empirical results on two new annotated satellite videos
reconfirm the applicability of this approach for vehicle detection. They more
importantly indicate that pre-training on WAMI data and then fine-tuning on few
annotated video frames for a new video is sufficient. In our experiment only
five annotated images yield a $F_1$ score of 0.81 on a new video showing more
complex traffic patterns than the Las Vegas video. Our best result on Las Vegas
is a $F_1$ score of 0.87 which makes the proposed approach a leading method for
this benchmark.
Related papers
- VFM-Det: Towards High-Performance Vehicle Detection via Large Foundation Models [21.186456742407007]
We propose a new vehicle detection paradigm based on a pre-trained foundation vehicle model (VehicleMAE) and a large language model (T5), termed VFM-Det.
Our model improves the baseline approach by $+5.1%$, $+6.2%$ on the $AP_0.5$, $AP_0.75$ metrics, respectively.
arXiv Detail & Related papers (2024-08-23T12:39:02Z) - XLD: A Cross-Lane Dataset for Benchmarking Novel Driving View Synthesis [84.23233209017192]
This paper presents a novel driving view synthesis dataset and benchmark specifically designed for autonomous driving simulations.
The dataset is unique as it includes testing images captured by deviating from the training trajectory by 1-4 meters.
We establish the first realistic benchmark for evaluating existing NVS approaches under front-only and multi-camera settings.
arXiv Detail & Related papers (2024-06-26T14:00:21Z) - Vehicle Perception from Satellite [54.07157185000604]
The dataset is constructed based on 12 satellite videos and 14 synthetic videos recorded from GTA-V.
It supports several tasks, including tiny object detection, counting and density estimation.
128,801 vehicles are annotated totally, and the number of vehicles in each image varies from 0 to 101.
arXiv Detail & Related papers (2024-02-01T15:59:16Z) - Tracking Everything Everywhere All at Once [111.00807055441028]
We present a new test-time optimization method for estimating dense and long-range motion from a video sequence.
We propose a complete and globally consistent motion representation, dubbed OmniMotion.
Our approach outperforms prior state-of-the-art methods by a large margin both quantitatively and qualitatively.
arXiv Detail & Related papers (2023-06-08T17:59:29Z) - AutoShot: A Short Video Dataset and State-of-the-Art Shot Boundary
Detection [70.99025467739715]
We release a new public Short video sHot bOundary deTection dataset, named SHOT.
SHOT consists of 853 complete short videos and 11,606 shot annotations, with 2,716 high quality shot boundary annotations in 200 test videos.
Our proposed approach, named AutoShot, achieves higher F1 scores than previous state-of-the-art approaches.
arXiv Detail & Related papers (2023-04-12T19:01:21Z) - Video-based Smoky Vehicle Detection with A Coarse-to-Fine Framework [20.74110691914317]
We introduce a real-world large-scale smoky vehicle dataset with 75,000 annotated smoky vehicle images.
We also build a smoky vehicle video dataset including 163 long videos with segment-level annotations.
We present a new Coarse-to-fine Deep Smoky vehicle detection framework for efficient smoky vehicle detection.
arXiv Detail & Related papers (2022-07-08T06:42:45Z) - Real Time Monocular Vehicle Velocity Estimation using Synthetic Data [78.85123603488664]
We look at the problem of estimating the velocity of road vehicles from a camera mounted on a moving car.
We propose a two-step approach where first an off-the-shelf tracker is used to extract vehicle bounding boxes and then a small neural network is used to regress the vehicle velocity.
arXiv Detail & Related papers (2021-09-16T13:10:27Z) - Vehicle Position Estimation with Aerial Imagery from Unmanned Aerial
Vehicles [4.555256739812733]
This work describes a process to estimate a precise vehicle position from aerial imagery.
The state-of-the-art deep neural network Mask-RCNN is applied for that purpose.
A mean accuracy of 20 cm can be achieved with flight altitudes up to 100 m, Full-HD resolution and a frame-by-frame detection.
arXiv Detail & Related papers (2020-04-17T12:29:40Z) - Drone-based RGB-Infrared Cross-Modality Vehicle Detection via
Uncertainty-Aware Learning [59.19469551774703]
Drone-based vehicle detection aims at finding the vehicle locations and categories in an aerial image.
We construct a large-scale drone-based RGB-Infrared vehicle detection dataset, termed DroneVehicle.
Our DroneVehicle collects 28, 439 RGB-Infrared image pairs, covering urban roads, residential areas, parking lots, and other scenarios from day to night.
arXiv Detail & Related papers (2020-03-05T05:29:44Z) - On Learning Vehicle Detection in Satellite Video [0.0]
Vehicle detection in aerial and satellite images is still challenging due to their tiny appearance in pixels compared to the overall size of remote sensing imagery.
This work proposes to apply recent work on deep learning for wide-area motion imagery (WAMI) on satellite video.
arXiv Detail & Related papers (2020-01-29T15:35:16Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.