The DLR HyperSpectral Unmixing (DLR HySU) open benchmark dataset includes airborne hyperspectral and RGB imagery of targets of different materials and sizes on a homogeneous background, complemented by simultaneous ground-based reflectance measurements. The dataset allows assessing dimensionality estimation, endmember extraction with and without pure pixel assumption, and abundance estimation in the frame of spectral unmixing applications, enabling estimations at sub-pixel level. This paper presents the first works in the literature using the dataset, which demonstrate that DLR HySU is filling a gap regarding validation using real imaging spectrometer data with accurately measured targets.

Multi-class vehicle detection from airborne imagery with orientation estimation is an important task in the near and remote vision domains with applications in traffic monitoring and disaster management. In the last decade, we have witnessed significant progress in object detection in ground imagery, but it is still in its infancy in airborne imagery, mostly due to the scarcity of diverse and large-scale datasets. Despite being a useful tool for different applications, current airborne datasets only partially reflect the challenges of real-world scenarios. To address this issue, we introduce EAGLE (oriEnted vehicle detection using Aerial imaGery in real-worLd scEnarios), a large-scale dataset for multi-class vehicle detection with object orientation information in aerial imagery. It features high-resolution aerial images composed of different real-world situations with a wide variety of camera sensor, resolution, flight altitude, weather, illumination, haze, shadow, time, city, country, occlusion, and camera angle. The annotation was done by airborne imagery experts with small-and large-vehicle classes. EAGLE contains 215,986 instances annotated with oriented bounding boxes defined by four points and orientation, making it by far the largest dataset to date in this task. It also supports researches on the haze and shadow removal as well as super-resolution and in-painting applications. We define three tasks: detection by (1) horizontal bounding boxes, (2) rotated bounding boxes, and (3) oriented bounding boxes. We carried out several experiments to evaluate several state-of-the-art methods in object detection on our dataset to form a baseline. Experiments show that the EAGLE dataset accurately reflects real-world situations and correspondingly challenging applications. The dataset will be made publicly available.

The fusion of complementary information from co-registered multi-modal image data enables a more detailed and more robust understanding of an image scene or specific objects, and is important for several applications in the field of remote sensing. In this paper, the benefits of combining RGB, near infrared (NIR) and thermal infrared (TIR) aerial images for the task of semantic vehicle segmentation through deep neural networks are investigated. Therefore, RGB, NIR and TIR image triplets acquired by the Modular Aerial Camera System (MACS) are precisely co-registered through the application of a virtual camera system and subsequently used for the training of different neural network architectures. Various experiments were conducted to investigate the influence of the different sensor characteristics and an early or late fusion within the network on the quality of the segmentation results.

This article describes the workflow of the classification algorithm which ranked at 2ndplace in the 2018 GRSS Data Fusion Contest. The objective of the contest was to provide a classification map with 20 classes on a complex urban scenario. The available multi-modal data were acquired from hyperspectral, LiDAR and very high-resolution RGB sensors flown on the same platform over the city of Houston, TX, USA. The classification was obtained by merging deep convolutional and shallow fully-connected neural networks on a simplified set of classes, complemented by a series of specific detectors and ad hoc classifiers.

Significantly outperforming traditional machine learning methods, deep convolutional neural networks have gained increasing popularity in the application of image classification and segmentation. Nevertheless, deep learning-based methods usually require a large amount of training data, which is quite labor-intensive and time-demanding. To deal with the problem in generating training data, we propose in this paper a novel approach to generate image annotations by transferring labels from aerial images to UAV images and refine the annotations using a densely connected CRF model with an embedded naive Bayes classifier. The generated annotations not only present correct semantic labels, but also preserve accurate class boundaries. To validate the utility of these automatic annotations, we deploy them as training data for pixel-wise image segmentation and compare the results with the segmentation using manual annotations. Experiment results demonstrate that the automatic annotations can achieve comparable segmentation accuracy as the manual annotations.

Despite the existence of various matching algorithms, matching of images from Micro Aerial Vehicles (MAVs) and airplanes is still a tough problem due to the substantial differences in scale and rotation. This paper investigates the fusion of MAV imagery and airplane imagery and proposes a new robust image matching method with self-adaption to differences in scale and viewing direction. This method is further applied to register a MAV image block with reference to the orthophoto and DSM of a previously-geolocalized aerial image dataset. After registration, a fused 3D point cloud is generated and then combined with images as inputs for land cover (here roofs) classification. Experiments show that the proposed matching method outperforms SIFT/ASIFT methods in both quantity and reliability of matching results, while the registration of MAV imagery achieves decimeter-level accuracy without using any onboard GPS/IMU data. Besides, the pixel-level classification that integrates information of point clouds and images achieves significantly higher accuracy than simply image-based classification.

Vehicle detection in dense urban areas is often complicated due to car-like objects on rooftops which result in false positive detections. This can be easily avoided by using a digital surface model (DSM) calculated from two consecutive images to exclude those regions. However, in the real-time case traffic information has to be gathered rapidly and the calculation of the DSM for the whole image takes a lot of time. The presented approach suggest a method where the disparity image is only calculated for areas of interest. These areas are selected by projecting the road segments from a road database in the original image using the collinearity equation. The local coordinates of the detected vehicles are then transformed back in the UTM coordinate system using the collinearity equation again. It can be shown that the search area for the detector is significantly reduced and which also leads to improved results of the detection.

A new approach for the traffic congestion detection in time series of optical digital camera images is proposed. It is well suited to derive various traffic parameters such as vehicle density, average vehicle velocity, beginning and end of congestion, length of congestion or for other traffic monitoring applications. The method is based on the vehicle detection on the road segment by change detection between two images with a short time lag, the usage of a priori information such as road data base, vehicle sizes and road parameters and a simple linear traffic model based on the spacing between vehicles. The estimated velocity profiles for experimental data acquired by airborne optical remote sensing sensor - 3 K camera system - coincide quite well with the reference measurements.