Christina Grönwall

Ground Target Recognition Using Rectangle Estimation

We propose a ground target recognition method based on 3-D laser radar data. The method handles general 3-D scattered data. It is based on the fact that man-made objects of complex shape can be decomposed to a set of rectangles. The ground target recognition method consists of four steps; 3-D size and orientation estimation, target segmentation into parts of approximately rectangular shape, identification of segments that represent the targets functional/main parts, and target matching with CAD models. The core in this approach is rectangle estimation. The performance of the rectangle estimation method is evaluated statistically using Monte Carlo simulations. A case study on tank recognition is shown, where 3-D data from four fundamentally different types of laser radar systems are used. Although the approach is tested on rather few examples, we believe that the approach is promising

An approach to target detection in forested scenes

Laser-based 3D sensors measure range with high accuracy and allow for detection of several reflecting surfaces for each emitted laser pulse. This makes them particularly suitable for sensing objects behind various types of occlusion, e.g. camouflage nets and tree canopies. Nevertheless, automatic detection and recognition of targets in forested areas is a challenging research problem, especially since foreground objects often cause targets to appear as fragmented. In this paper we propose a sequential approach for detection and recognition of man-made objects in natural forest environments using data from laser-based 3D sensors. First, ground samples and samples too far above the ground (that cannot possibly originate from a target) are identified and removed from further processing. This step typically results in a dramatic data reduction. Possible target samples are then detected using a local flatness criterion, based on the assumption that targets are among the most structured objects in the remaining data. The set of samples is reduced further through shadow analysis, where any possible target locations are found by identifying regions that are occluded by foreground objects. Since we anticipate that targets appear as fragmented, the remaining samples are grouped into a set of larger segments, based on general target characteristics such as maximal dimensions and generic shape. Finally, the segments, each of which corresponds to a target hypothesis, undergo automatic target recognition in order to find the best match from a model library. The approach is evaluated in terms of ROC on real data from scenes in forested areas.

Simulation and modeling of laser range profiling and imaging of small surface vessels

Abstract. The detection and classification of small surface targets at long ranges is a growing need for naval security. Simulations of a laser radar at 1.5 μm aimed for search, detect, and recognition of small maritime targets will be discussed. The data for the laser radar system will be based on present and realistic future technology. The simulated data generate signal waveforms for every pixel in the sensor field-of-view. From these we can also generate two-dimensional (2-D) and three-dimensional (3-D) range and intensity images. The simulations will incorporate typical target movements at different sea states, vessel courses, effects of the atmospheric turbulence and also include different beam jitter. The laser pulse energy, repetition rate as well as the receiver and detector parameters have been the same during the simulations. We have also used a high resolution (sub centimeter) laser radar based on time correlated single photon counting to acquire examples of range profiles from different small model ships. The collected waveforms are compared with simulated wave forms based on 3-D models of the ships. A discussion of the classification potential based on information in 1-D, 2-D, and 3-D data separately and in combination is made versus different environmental conditions and system parameters.

Spatial filtering for detection of partly occluded targets

A Bayesian approach for data reduction based on spatial filtering is proposed that enables detection of targets partly occluded by natural forest. The framework aims at creating a synergy between terrain mapping and target detection. It is demonstrates how spatial features can be extracted and combined in order to detect target samples in cluttered environments. In particular, it is illustrated how a priori scene information and assumptions about targets can be translated into algorithms for feature extraction. We also analyze the coupling between features and assumptions because it gives knowledge about which features are general enough to be useful in other environments and which are tailored for a specific situation. Two types of features are identified, nontarget indicators and target indicators. The filtering approach is based on a combination of several features. A theoretical framework for combining the features into a maximum likelihood classification scheme is presented. The approach is evaluated using data collected with a laser-based 3-D sensor in various forest environments with vehicles as targets. Over 70% of the target points are detected at a false-alarm rate of <1%. We also demonstrate how selecting different feature subsets influence the results.

An information system for target recognition

We present an approach to a general decision support system. The aim is to cover the complete process for automatic target recognition, from sensor data to the user interface. The approach is based on a query-based information system, and include tasks like feature extraction from sensor data, data association, data fusion and situation analysis. Currently, we are working with data from laser radar, infrared cameras, and visual cameras, studying target recognition from cooperating sensors on one or several platforms. The sensors are typically airborne and at low altitude. The processing of sensor data is performed in two steps. First, several attributes are estimated from the (unknown but detected) target. The attributes include orientation, size, speed, temperature etc. These estimates are used to select the models of interest in the matching step, where the target is matched with a number of target models, returning a likelihood value for each model. Several methods and sensor data types are used in both steps. The user communicates with the system via a visual user interface, where, for instance, the user can mark an area on a map and ask for hostile vehicles in the chosen area. The user input is converted to a query in ΣQL, a query language developed for this type of applications, and an ontological system decides which algorithms should be invoked and which sensor data should be used. The output from the sensors is fused by a fusion module and answers are given back to the user. The user does not need to have any detailed technical knowledge about the sensors (or which sensors that are available), and new sensors and algorithms can easily be plugged into the system.

Continuously scanning time-correlated single-photon-counting single-pixel 3-D lidar

Abstract. Time-correlated single-photon-counting (TCSPC) lidar provides very high resolution range measurements. This makes the technology interesting for three-dimensional imaging of complex scenes with targets behind foliage or other obscurations. TCSPC is a statistical method that demands integration of multiple measurements toward the same area to resolve objects at different distances within the instantaneous field-of-view. Point-by-point scanning will demand significant overhead for the movement, increasing the measurement time. Here, the effect of continuously scanning the scene row-by-row is investigated and signal processing methods to transform this into low-noise point clouds are described. The methods are illustrated using measurements of a characterization target and an oak and hazel copse. Steps between different surfaces of less than 5 cm in range are resolved as two surfaces.

Atmospheric turbulence effects in single-photon counting time-of-flight range profiling

In several laser radar applications detection of targets with high resolution and range accuracy, is of importance. Time-of-flight time-correlated single-photon counting (TCSPC) provides a method to accomplish range profiling at longer ranges with high accuracy and resolution. The performance of a TCSPC system used for optical range profiling suffers from the influence of atmospheric turbulence effects causing perturbations of the registered time histograms. This is mostly manifested in propagation paths close to the ground. In this work a TCSPC system based on a monostatic transmitter/receiver head, a picosecond laser operating at high pulse-repetition frequency, a single photon detector and acquisition electronics with high timing resolution was used to study the influence from atmospheric turbulence on registered pulse responses from test targets. The turbulence conditions were monitored during the experiments and the influence from turbulence effects on the pulse response are discussed. The experimental results are considered in relation to existing turbulence models. Implications on system performance for a TCSPC time-of-flight range profiling system are illustrated.

Registration and change detection techniques using 3D laser radar data from natural environments

In this paper, we present techniques related to registration and change detection using 3D laser radar data. First, an experimental evaluation of a number of registration techniques based on the Iterative Closest Point algorithm is presented. As an extension, an approach for removing noisy points prior to the registration process by keypoint detection is also proposed. Since the success of accurate registration is typically dependent on a satisfactorily accurate starting estimate, coarse registration is an important functionality. We address this problem by proposing an approach for coarse 2D registration, which is based on detecting vertical structures (e.g. trees) in the point sets and then finding the transformation that gives the best alignment. Furthermore, a change detection approach based on voxelization of the registered data sets is presented. The 3D space is partitioned into a cell grid and a number of features for each cell are computed. Cells for which features have changed significantly (statistical outliers) then correspond to significant changes.

Performance analysis of measurement error regression in direct-detection laser radar imaging

In this paper a tool for synthetic generation of scanning laser radar data is described and its performance is evaluated. By analyzing data from the system, we recognize objects on the ground. In the measurement system it is possible to add several design parameters, which make it possible to test an estimation scheme under different types of system design. The measurement system model includes laser characteristics, object geometry, reflection, speckles, atmospheric attenuation, turbulence and a direct detection receiver. A parametric method that estimates an objects size and orientation is described. There are measurement errors present and thus, the parameter estimation is based on a measurement error model. The parameter estimation accuracy is limited by the Cramer-Rao lower bound. Validations of both the measurement error model and the measurement system are shown. Data from both models generate parameter estimates that are close to the Cramer-Rao lower bound.

Least Squares Fitting Articulated Objects

In safety and security applications, one issue is target recognition. In some recognition processes, for vehicle recognition, we must take into account that the target maybe articulated. Vehicles can easily change shape by opening of a door, adding of load etc.This change of shape can be moddled as an articulation. if the articluation of model the target also can be moddled, the mathcing with library modles can be improved. In this paper we propose a method for modular least squares fitting of two 3D point scatters with points correspondence. A method for least squares fitting of a 3D point scatter and a CAD (face) models is also proposed. An example pf modular leats squares fitting two #D point scatters,based on simulated data, is known.