Ovitraps are a widely used method for mosquito detection and monitoring, especially Aedes mosquitoes. Eggs present in ovitraps must be routinely counted to generate up-to-date information on potential spread of mosquito-borne diseases. This task is tedious, time consuming and prone to errors if done manually by eye counting. In this contribution, we introduce the Ovitrap Monitor, an online open source and user-friendly integrated application that semi-automatically counts mosquito eggs from low-medium resolution mobile phone pictures. A high correlation was found between counts performed manually by a technician and those obtained with the app using an extensive dataset of more than 750 ovitrap pictures. The application features an intuitive user interface and time-series plots and maps to facilitate data flow and speed up evidence-based decision-making within health organisations battling mosquito-borne diseases. Besides being open source, the Ovitrap Monitor is also backed by test data to guarantee its implementation through benchmarking and enforce research in the public health field.

Oviposition measurement with ovitraps is one of the most widely used methods to monitor Aedes aegypti mosquito activity in the world. Egg counting is however very time consuming. This paper presents the semi -automatic counting of mosquito eggs laid on ovitrap sticks in images acquired by cellular phones. In Cordoba, Argentina, 150 ovitraps were distributed in the city to measure the evolution of the Aedes aegypti population, estimated indirectly by the number of laid eggs. An important increase in the counts is a potential indicator of an imminent outbreak, alerting the health services to warn the population and recall the good sanitary practices. Bringing image processing to this proj ect is a way to relieve the technician from the tedious egg counting behind a magnifier and to reduce the count errors due to distraction or fatigue. We developed a fast semiautomatic counting solution with tools to focus on the useful image area, to show the confidence of automatic count numbers and to handle the collection of results.

Image registration, the task of aligning two images, is a fundamental operation for applications like image stitching or image comparison. In our project in surveillance for route clearance operations, a drone will be used to detect suspicious people and vehicles. This paper presents an approach for real-time image alignment of video images acquired by a moving camera. The high correlation between successive images allows for relatively simple algorithms. We considered region segmentation as an alternative to the more classical corner or interest point detectors and evaluated the appropriateness of connected component labeling with a connectivity defined by the gray-level similarity between neighboring pixels. Real-time processing is intended thanks to a very fast segment-based (as opposed to pixel-based) connected component labeling. The regions, even if not always pleasing the human eye, proved stable enough to be linked across images by trivial features such as the area and the centroid. The vector shifts between matching regions were filtered and modeled by an affine transform. The paper discusses the execution time obtained by this feasibility study for all the steps needed for image registration and indicates the planned improvements to achieve real-time.

This paper presents a method for trajectory extraction in videos acquired with a slightly moving camera. Trajectories are initialized at Shi-Tomasi [1] feature points and tracked thanks to the Lucas-Kanade [2] algorithm from the openCV library [3]. New feature points are regularly introduced to compensate for track losses and to handle newly appeared objects. A simple and fast method for camera motion compensation has been implemented, using the fact that near static scene points undergo an equal translation between any two images. Local histograms of displacement normally exhibit a clear peak since our application considers scenes with relatively few moving targets. These peaks designate which tracks and thus which points are best to estimate the homographies representing motion between frames of the sequence. Tracking results for pedestrian and vehicles with camera motion compensation are shown and discussed for two test cases with different environment, scenario and different video quality. The usefulness of camera motion compensated trajectories is demonstrated by an example of target classification based on track maximal speed and possible hotspot detection from long track pauses.

In the field of aerial surveillance, tracking targets in images is complicated by the possible motion of the camera, especially if frame differencing is used to detect moving objects. We propose in this paper to exploit the high similarity in sequences acquired from a nearly static camera. In this case distance maps grown from image edge points share many similarities and T-junctions of distance map skeletons appear to offer precisely located reference points. Each T-junction is attributed seven features: the value in the distance map, three orientations of the junction branches and R,G, B image intensities. Registering images is carried out on a division of the images into tiles, looking for the dominant translation per tile of matching T-junction points. The obtained displacement field allow for the compensation of small camera motion. This was tested on image sequences captured by a smartphone held in hand while targeting a given static scene with a few moving vehicles and pedestrians.

This chapter describes the research activities of the Royal Military Academy on remote sensing applied to mine action. Remote sensing can be used to detect specific features that could lead to the suspicion of the presence, or absence, of mines. Work on the automatic detection of trenches and craters is presented here. Land cover can be extracted and is quite useful to help mine action. We present here a classification method based on Gabor filters. The relief of a region helps analysts to understand where mines could have been laid. Methods to be a digital terrain model from a digital surface model are explained. The special case of multi‐spectral classification is also addressed in this chapter. Discussion about data fusion is also given. Hyper‐spectral data are also addressed with a change detection method. Synthetic aperture radar data and its fusion with optical data have been studied. Radar interferometry and polarimetry are also addressed.

Digital terrain models (DTMs) are of significant interest for applications such as environment planning, flood risk assessment or building detection. A digital surface model (DSM) can be obtained efficiently in both time and cost from light detection and ranging (lidar) acquisition or from digital photogrammetry with aerial or satellite stereoscopic imagery. A DTM can be derived from a DSM if the distinction between ground and non-ground pixels can be automated. We propose in this article a new automatic DSM-to-DTM transform targeting urban areas. Our approach segments the DSM twice: first to get large uniform regions normally corresponding to the road network and attached town squares, and second to obtain smoother areas. Smoother DSM areas overlapping the large regions are selected to populate the DTM, which is then completed by a hierarchical interpolation procedure. As a refinement step, unused smoother regions lying under this DTM are added to create, after interpolation, the final DTM. This approach is positioned relative to the literature about segmentation-based lidar ground filtering. The procedure was developed for DSM rasters. Since the DTM extraction is intended to be applied to large images, special attention was devoted to optimize image processing tasks relative to memory usage and execution time. The proposed development was integrated in a building detection procedure and validated qualitatively in the context of a benchmark on urban object detection of the International Society for Photogrammetry and Remote Sensing (ISPRS). It was also applied to Brussels data for which lidar DTMs are available. The DTM comparison supports the correctness of our solution although difficulties may be encountered in off-terrain regions surrounded by higher regions and some interiors of city blocks. A final test on a rural and peri-urban scene opens positive perspectives for scenes more general than urban areas.

Epipolar rectification aims at resampling stereoscopic images so that conjugate points are located along the same horizontal x-axis. For most stereoscopic digital surface model production algorithms, this rectification is a necessary preprocessing task because it allows reducing the 2D matching to a 1D matching problem. Most epipolar rectification algorithms exist in literature and are mainly for a given type of sensor (frame camera or push-broom sensor). In this paper, we present a generic method for epipolar rectification. This means that the method is applicable for both frame and push-broom cameras. The only difference lies in the projection function used to generate epipolar curves.

During the Non-Technical Survey, information on a Suspected Hazardous Area (SHA) is collected and analysed for assessment and reduction/inclusion purposes. This phase focuses on a scale that is more local than the Advanced General Survey (WP210). Unlike the Technical Survey, the Non-Technical Survey does not involve entering the SHA physically. This deliverable, entitled Non-Technical Survey Tool Performance evaluation report, is the fourth deliverable devoted to tools for Non-Technical Survey (NTS). It includes a description of the tools developed, the rationale and guidelines for using them and an evaluation of their performance. It is meant to be a reference document on WP220 tools and services after the project lifetime. Therefore, it is as much as possible self-contained and includes more than the description of the work achieved during the last period.

This paper presents an automatic building detection approach exploiting colour infrared (CIR) imagery. A Digital Surface Model (DSM) is first extracted by photogrammetry with a proprietary development including multiple views. Then a Digital Terrain Model (DTM) is derived from the DSM by selecting the lowest regions with slowly varying elevation. A normalised DSM, difference of the DSM and derived DTM highlights building candidates thanks to a simple threshold. In order to reduce false positives due to trees, a vegetation mask is obtained from the NDVI of the orthorectified CIR image. A specific procedure was designed to handle the problematic shadow areas where the NDVI criterion often misses vegetation. The proposed building detection approach has been applied to the Vaihingen data set of the ISPRS benchmark and validated by the results of its evaluation procedure. We plan to integrate the new DTM extraction and shadow adapted vegetation mask, main contributions of this paper, to our project about change detection for database revision for the Belgian National Geographic Institute.

This article introduces a novel structured light pattern designed to be compatible with the spatial light modulator (SLM) projection. The proposed pattern is a De Bruijn-based sequence applied to a combination of continuous and dashed lines for the pattern. The sequence is coded in the period and duty cycles of the dashed lines. It provides 16 different lines which limits to two the required number of dashed lines needed for identification. The segmentation has been made easier by alternating continuous and dashed lines. As required by the use of SLMs, the sequence has been adapted by making it symmetric. It has been improved by guaranteeing a hamming distance equal to two for two successive dashed lines. The implementation on a virtual model has shown that a subpixel accuracy has been achieved. This pattern has been developped for 3-D endoscopy.

This paper deals with building change detection by supervised classification of image regions into 'built' and 'non-built' areas. Regions are the connected components of low gradient values in a multi-spectral aerial image. Classes are learnt from spectral (colour, vegetation index) and elevation cues relatively to building polygons and non building areas as defined in the existing database. Possible candidate building regions are then filtered by geometrical features. Inconsistencies in the database with the recent image are automatically detected. Tests in cooperation with the Belgian National Geographical Institute on an area with sufficient buildings and landscape variety have shown that the system allows for the effective verification of unchanged buildings, and detection of destructions and new candidate buildings.

This paper presents speed estimation of a moving object thanks to two images captured within a known time interval from one stationary un-calibrated camera. The development is currently applicable to rigid objects animated by a pure translation and requires the localization of corresponding points in both images and the specification of one real dimension. An interesting solution based on an equivalent stereo problem is suggested. It considers the object stationary and searches for the virtual camera motion which would produce the same images. The mathematical formulation is simple using 3D vectors and the camera parameters: focal length, CCD size and pixel size. The developed software package was tested for vehicle speed second assessment of the velocity captured by the LIDAR system LMS-06 distributed by secuRoad SA.

This paper presents a supervised classification method applied to building change detection in VHR aerial images. Multi-spectral stereo pairs of 0.3m resolution have been processed to derive elevation, vegetation index and colour features. These features help filling a 5-dimensional histogram whose bins finally hold the ratio of built-up and non built-up pixels, according to the vector database to be updated. This ratio is used as building confidence at each pixel to issue a building confidence map from which to perform building verification and detection. The implementation based on histogram is very simple to code, very fast in execution and compares in this application to a state-of-the-art supervised classifier. It has been tested for the Belgian National Mapping Agency (IGN) to identify areas with high probability of change in building layers.

A method is proposed for building and road detection on very high spatial resolution multispectral aerial image of dense urban areas. First, objects are extracted with a segmentation algorithm in order to use both spectral and spatial information. Second, a spectral-spatial object-level pattern is formed, and then classification is performed using a 3-class SVM classifier, followed by a post-processing using contextual information to handle conflicts. However, in the particular case where many building roofs are grey like the roads and have similar geometry, classification accuracy is inevitably limited. In order to overcome this limitation, different classifiers are combined and different patterns used, improving the accuracy of 10%.

The availability of stereo couples of satellite or aerial images allows for the extraction of the Digi tal Surface Model which is of high importance for earth observation. In the specific c ase of change detection of man made structures, the 3D information is a vital cue to distinguish buildings from flat objects (e.g. parki ng lots). Height variations are obtained from a dis parity map, qualifying the magnitude of the parallax and henceforth the relati ve elevation. If available, the camera and flight p arameters enable other types of applications thanks to the derivation of geographic al 3-D coordinates. In particular, the National Geo graphic Institute of Belgium is interested in automatic estimation of 3D coordinate s o support the nowadays time consuming manual pro cedure. In a first collaboration with NGI, we developed two disparity estimation procedures to detect buildings and look f r related changes in the topographic database. Then flight and camera data w ere used to derive geographical 3D coordinates. This paper first recalls how the different steps ne cessary to produce a DSM from stereo images were im plemented, addressing epipolar rectification, disparity estimation and 3D reconstruction. The major contribution of the pape r is to present a quantitative assessment of the quality of automatic 3D measures by comparison with available ground truth values. A separation between errors from artefacts in disparity estimation and precisio n l mits in the reconstruction process has been con sidered.

A method is proposed for building and road detection on VHR multispectral aerial images of dense urban areas. Spatial and spectral features of segmented areas are classified using a 3-class SVM integrating some a priori and contextual information to handle unclassified patterns and conflicts. Geometrical object features and additional information improve the classification accuracy in the difficult case where many building roofs are grey like the roads and have similar geometry. Also, road network regularization is suggested to improve the classification accuracy.