Floods are an increasingly common global threat, causing emergencies and severe damage to infrastructure. During crises, organisations such as the World Food Programme use remotely sensed imagery, typically obtained t...
详细信息
ISBN:
(数字)9798350360325
ISBN:
(纸本)9798350360332
Floods are an increasingly common global threat, causing emergencies and severe damage to infrastructure. During crises, organisations such as the World Food Programme use remotely sensed imagery, typically obtained through drones, for rapid situational analysis to plan life-saving actions. Computer Vision tools are needed to support task force experts on-site in the evaluation of the imagery to improve their efficiency and to allocate resources strategically. We introduce the BlessemFlood21 dataset to stimulate research on efficient flood detection tools. The imagery was acquired during the 2021 Erftstadt-Blessem flooding event and consists of high-resolution and georeferenced RGB-NIR images. In the resulting RGB dataset, the images are supplemented with detailed water masks, obtained via a semi-supervised human-in-the-loop technique, where in particular the NIR information is leveraged to classify pixels as either water or non-water. We evaluate our dataset by training and testing established Deep learning models for semantic segmentation. With BlessemFlood21 we provide labeled high-resolution RGB data and a baseline for further development of algorithmic solutions tailored to flood detection in RGB imagery.
Floods are an increasingly common global threat, causing emergencies and severe damage to infrastructure. During crises, organisations such as the World Food Programme use remotely sensed imagery, typically obtained t...
详细信息
Object detection in aerial images is an important task in environmental, economic, and infrastructure-related tasks. One of the most prominent applications is the detection of vehicles, for which deep learning approac...
详细信息
The need for accurate yield estimates for viticulture is becoming more important due to increasing competition in the wine market worldwide. One of the most promising methods to estimate the harvest is berry counting,...
详细信息
High-quality positioning is of fundamental importance for an increasing variety of advanced driver assistance systems. GNSS-based systems are predominant outdoors but usually fail in enclosed areas where a direct line...
详细信息
High-quality positioning is of fundamental importance for an increasing variety of advanced driver assistance systems. GNSS-based systems are predominant outdoors but usually fail in enclosed areas where a direct line-of-sight to satellites is unavailable. For those scenarios, external infrastructure-based positioning systems are a promising alternative. However, external position detections have no identity information as they may belong to any object, i.e. they are anonymous. Moreover, the area covered by external sensors may contain gaps where objects cannot be observed leading to a correspondence problem between multiple detections and actual objects. We present a global tracking-by-identification approach as extension to existing local trackers that uses odometry sensor data of vehicles to find the corresponding subset of external detections. Thus, our approach enables the assignment of anonymous external detections to a specific vehicular endpoint and the estimation of its current position without requiring an initial location. The problem is decomposed resulting in a two step approach. The first algorithm determines possible track segment combinations which are used as track hypotheses. The track hypothesis generation algorithm considers spatio-temporal relationships between track segments, thus avoiding exponentially growing complexity inherent to data association problems. The second algorithm compares track hypotheses to the relative vehicle trajectory using pseudo-distance correlation metrics. In a detailed evaluation, we demonstrate that the proposed approach is able to reliably perform global tracking and identification of camera-observed vehicles in real-time, despite relatively large coverage gaps of the external sensors.
暂无评论