X-SectionScope

A volumetric display system that creates a distortion-free three-dimensional (3D) image in midair using a novel imaging system is reported. A roof mirror array forms an aerial real image with an image deformation by retroreflection. The image deformation can be reduced by constructing an imaging system using two roof mirror arrays arranged in a parallel manner. A cross-sectional image of a 3D object is formed by the proposed imaging system in midair and swept by a galvanometer mirror scanner to create a 3D volume image. An aerial 3D volume image formation without the image deformation was confirmed by an experimental volumetric display system.

AIRR (aerial imaging by retro-reflection) is an aerial-image-forming technique [1]. To give a sense to the aerial image formed with AIRR, we have developed an interactive system with the aerial image using Kinect [2]. Furthermore, multi-modal aerial display has been developed in combination of a warm aerial image formed with double-layered arrays of rectangular mirrors (WARM) and an aerial visual image with AIRR [3].

This paper proposes the localization algorithm that estimates translation parameters of an aircraft by comparing the sampled elevation map recovered from aerial sequence images, and the digital elevation model (DEM) with the given orientation and altitude parameters obtained from a gyroscope. It consists of two stages: recovering the sampled elevation map from multiple aerial image pairs and matching of the relative recovered elevation map (REM) with the relative DEM. Computer simulations with three real aerial image sequences show the effectiveness of the proposed algorithm.

Binocular stereo vision processes estimate 3D surfaces using a pair of images taken from different points of view. Three-dimensional surface characteristics are estimated by matching 2D image areas or features corresponding to the projections of the same 3D points. The most classic area-based methods used cross correlation with a fixed window-size, but this technique presents a major drawback: the computation of depth is generally prone to errors close to surface discontinuities. In this paper, we present our current work on aerial stereo images of urban areas. A correlation-based algorithm, with an adaptive window-size constrained by an edge map extracted from the images, is presented. This technique is not used to refine an initial disparity map but to create one with good discontinuities location. The algorithm follows three steps: first, window sizes for each pixel are computed; second, a disparity map is created; third, map completion is performed and a final dense disparity map with subpixel precision is produced by Kanade correction. Experimental results on real aerial images are presented.

The ability to recognize Kauri trees from aerial images is crucial in the fight against Kauri Dieback disease. In this work, we propose an automatic Kauri recognition system, that harnesses modern Convolutional Neural Network technology in order to accurately segment Kauri trees from aerial images of forests. The proposed system initially segments images into homogeneous regions using morphological opening, Gaussian filtering and watershed segmentation; before training a classifier to differentiate between kauri segments and non-kauri segments. Experimental results demonstrate that the proposed system is capable of correctly classifying 93% of kauri segments it was provided with, based on drone aerial images and ground-truth data provided by experts.

Data Analytic interpretation of plant species is not widely explored. The image variety of plant species can be investigated with the help of machine learning and deep learning techniques. Machine learning and deep learning make the plant species investigation automated and almost accurate. In this paper, we have proposed a novel native and invasive plant species classification technique. We use the pre-trained deep convolution neural networks (transfer learning) to extract features from plant species and classify them into Native and Invasive. Here, state-of-the-art deep convolution neural network models like InceptionV3, MobileNetV2, ResNetV2, VGG16, and Xception have been explored to extract the feature vectors from images. Furthermore, the features of the images have been used for image classification using the Random Forest algorithm. The performance of the proposed system is verified on the proposed dataset (Native-Invasive) with aerial view images of native and invasive species. Results were obtained using cross-validation techniques. Our experiments demonstrate the potential of our proposed method for achieving excellent performance with a 95% accuracy using Xception with data augmentation, hyper-parameter optimization, and the Random Forest classification technique. The aerial images were captured and labeled by us which is very novel to our experimental setup. After using deep learning models we got promising results. The dataset used to train the plant species classifier will be made available on request.KeywordsFeature extractionTransfer learningRandom ForestDeep learningImage classificationNative plant speciesInvasive plant species

This paper presents a model-based approach for reconstructing 3D polyhedral building models from aerial images. The proposed approach exploits some geometric and photometric properties resulting from the perspective projection of planar structures. Data are provided by calibrated aerial images. The novelty of the approach lies in its featurelessness and in its use of direct optimization based on image rawbrightness. The proposed framework avoids feature extraction and matching. The 3D polyhedral model is directly estimated by optimizing an objective function that combines an image-based dissimilarity measure and a gradient score over several aerial images. The optimization process is carried out by the Differential Evolution algorithm. The proposed approach is intended to provide more accurate 3D reconstruction than feature-based approaches. Fast 3D model rectification and updating can take advantage of the proposed method. Several results and evaluations of performance from real and synthetic images show the feasibility and robustness of the proposed approach.

An important challenge to any image pixels classification system is to correctly assign each pixel to its proper class without blurring edges delimiting neighboring regions. In this paper, we present an aerial image mapping approach that advantageously combines unsupervised segmentation with a supervised Markov model based recognition. The originality of the proposed system carries on three concepts: the introduction of an auto-adaptive circular-like window size while applying our stochastic classification to preserve region edges, the extension of the Dependency Tree–HMM to permit the computation of likelihood probability on windows of different shapes and sizes and a mechanism that checks the coherence of the indexing by integrating both segmentations results: from unsupervised over segmentation, regions are assigned to the predominating class with a focus on inner region pixels. To validate our approach, we achieved experiments on real world high resolution aerial images. The obtained results outperform those obtained by supervised classification alone.KeywordsLand cover classificationhidden Markov modelaerial images

Counting people in crowds is a common problem in visual surveillance. Many solutions are just designed to count less than one hundred people. Only few systems have been tested on large crowds of several hundred people and no known counting system has been tested on crowds of several thousand people. Furthermore, none of these large scale systems delivers people's positions, they just estimate the number. But having the position of people would be a large benefit, since this would enable a human observer to carry out a plausibility check. In addition, most approaches require video data as input or a scene model. In order to generally solve the problem, these assumptions must not be made. We propose a system that can count people on single aerial images including mosaic images generated from video data. No assumptions about crowd density will be made, i. e. the system has to work from low to very high density. The main challenge is the large variety of possible input data. Typical scenarios would be public events such as demonstrations or open air concerts. Our system uses a model-based detection of individual humans. This includes the determination of their positions and the total number. In order to cope with the given challenges we divide our system into three steps: foreground segmentation, person size determination and person detection. We evaluate our proposed system on a variety of aerial images showing large crowds with up to several thousand people

We propose Fuwa-Vision, a simple interactive auto-stereoscopic display for multiple users, which does not require glasses or mechanical moving components. This system can project auto-stereoscopic images in midair with a simple structure. This provides a proper view of the combination of stereoscopic objects and real objects. In this setup, it can detect the location of the object, and allow the interaction with the 3D image. For example, it can detect the position of the candle, and render virtual flame for this candle as if it were with real fire.This display is consist of four parts, backlighted Liquid Crystal Display(LCD), transparent LCD, the Fresnel convex lens on the optical axis and the head tracking system for the viewer's position. It control the direction of light precisely.

Designing an optical aerial imaging system with high resolution and large fields of view (FoV) is a longstanding problem in remote sensing, astronomical observation, and geological exploration. In this paper, we propose a light field-guided optical synthetic aperture imaging system on master-slave unmanned aerial vehicles (UAVs). This system consists of single-master UAV and multiple-slave UAVs to capture cross-scale multiview aerial images to stitch an aerial image and even a video with high resolution and large FoV. However, relative poses of UAVs change dynamically during the flight, which causes the inaccuracy of large-FoV image stitching. To address this problem, we convert image stitching as a novel-view synthesis problem on a large-FoV light field. Under this insight, we construct a 5D light field to cover FoVs of all slave UAVs via Gaussian splatting technique. Then we exploit a light field-guided synthetic aperture imaging scheme to generate the high-resolution image. Additionally, this scheme can be extended for large-FoV video generation. Experimental results on real-world scenes show that the proposed imaging system is capable of generating the accurate, large-FoV, high-resolution image sequences. Hence, we believe that this system has great potential in large-FoV high-resolution aerial imaging.

Unmanned Aerial Vehicles (UAVs) are known for their speed and versatility in collecting aerial images and remote sensing for land use surveys and precision agriculture. With UAVs' growth in availability and accessibility, they are now of vital importance as technological support in marine-based applications such as vessel monitoring and search-and-rescue (SAR) operations. High-resolution cameras and Graphic processing units (GPUs) can be equipped on the UAVs to effectively and efficiently aid in locating objects of interest, lending themselves to emergency rescue operations or, in our case, precision aquaculture applications. Modern computer vision algorithms allow us to detect objects of interest in a dynamic environment; however, these algorithms are dependent on large training datasets collected from UAVs, which are currently time-consuming and labor-intensive to collect for maritime environments. To this end, we present a new benchmark suite, SeaD-roneSim, that can be used to create photo-realistic aerial image datasets with ground truth for segmentation masks of any given object. Utilizing only the synthetic data gen-erated from SeaDroneSim, we obtained 71 a mean Average Precision (mAP) on real aerial images for detecting our ob-ject of interest, a popular, open source, remotely operated underwater vehicle (BlueROV) in this feasibility study. The results of this new simulation suit serve as a baseline for the detection of the BlueROV, which can be used in underwater surveys of oyster reefs and other marine applications.

Due to the difficulty of acquiring real aerial infrared cloud images, we propose an efficient way to set up cloud simulation data set by particle system and texture synthesis, in order to alleviate the problem of data shortage. The deep network for cloud segmentation is trained on our simulation image data set, substantially decreasing the demand for real aerial cloud images. When testing on the real image data set, a satisfactory segmentation result with 79.64% has been reached which can meet the usage requirements. Our method can make the deep cloud segmentation network training feasible despite of the real image shortage, reducing the cost of data acquisition.

This paper demonstrates how to reduce the hand labeling effort considerably by 3D information in an object detection task. In particular, we demonstrate how an efficient car detector for aerial images with minimal hand labeling effort can be build. We use an on-line boosting algorithm to incrementally improve the detection results. Initially, we train the classifier with a single positive (car) example, randomly drawn from a fixed number of given samples. When applying this detector to an image we obtain many false positive detections. We use information from a stereo matcher to detect some of these false positives (e.g. detected cars on a facade) and feed back this information to the classifier as negative updates. This improves the detector considerably, thus reducing the number of false positives. We show that we obtain similar results to hand labeling by iteratively applying this strategy. The performance of our algorithm is demonstrated on digital aerial images of urban environments.

In this manuscript, we propose a system which can automatically recognize the oyster racks in an aerial image. As the oyster racks are recognized, the volume of the oysters could thus be estimated and the price can be predicted in advance. Besides that, when a disaster such as a typhoon strikes on the offshore, the loss could also be estimated when the numbers of oyster racks before and after the disaster are available for analysis. These information are useful for the local government in governing the aquaculture affairs. The advantage of the proposed system is to provide a useful tool in analyzing aquaculture information with less man power and time.