An important field of reasearch in computer vision is the 3D analysis and reconstruction of objects and scenes for e.g. position determination, online object recognition or collision prevention. Known techniques thereby mainly rely on measuring devices such as laser scanners, stereo camera systems, or comparable algorithms like structure from motion. The rather new Photonic Mixing Device (PMD) technique is based on the time-of-flight principle and measures full-range distance information in real-time. Unfortunately, PMD-based devices have still limited resolution (e.g. 160 x 120px) and provide only graylevel information. This paper describes a fast algorithmic approach to combine high resolution RGB images with low resolution PMD distance data, acquired using a binocular camera setup. The approach relies completely on fast parallel Graphics Processing Units (GPUs) ressources. Additionally, we introduce a simple but efficient method to detect insufficient color assignments, which are due to the binocular setup. The resulting combined RGBZ-data not only enhances the visual result, but also represents a basis for advanced data processing in e.g. object recognition.

This paper describes a system for detection and classification of moving objects based on support vector machines (SVM) and using 3D data. Two kinds of camera systems are used to provide the classification system with 3D range images: time-of-flight (TOF) camera and stereo vision system. While the former uses the modulated infrared lighting source to provide the range information in each pixel of a photonic mixer device (PMD) sensor, the latter employs the disparity map from stereo images to calculate three dimensional data. The proposed detection and classification system is used to classify different 3D moving objects in a dynamic environment under varying lighting conditions. The images of each camera are first preprocessed and then two different approaches are applied to extract their features. The first approach is a computer generated method which uses the principal component analysis (PCA) to get the most relevant projection of the data over the eigenvectors and the second approach is a human generated method which extracts the features based on some heuristic techniques. Two training data sets are derived from each image set based on heuristic and PCA features to train a multi class SVM classifier. The experimental results show that the proposed classifier based on range data from TOF camera is superior to that from the stereo system

In this work, a secure wireless sensor network (WSN) for the surveillance, monitoring and protection of critical infrastructures was developed. To guarantee the security of the system, the main focus was the implementation of a unique security concept, which includes both security on the communication level, as well as mechanisms that ensure the functional safety during its operation. While there are many theoretical approaches in various subdomains of WSNs—like network structures, communication protocols and security concepts—the construction, implementation and real-life application of these devices is still rare. This work deals with these aforementioned aspects, including all phases from concept-generation to operation of a secure wireless sensor network. While the key focus of this paper lies on the security and safety features of the WSN, the detection, localization and classification capabilities resulting from the interaction of the nodes’ different sensor types are also described.

A common way of performing phase-shift-based time-of-flight imaging combines the emission of a continuous-wave (CW) illumination signal with correlation with some reference signals at the detector array. This is the case for the well-known photonic mixer device (PMD), which correlates against displaced versions of the illumination control signal, at known phase shifts, and requires only four correlation values to estimate the phase shift. The main drawback of such approaches is that they require the assumption of nonrealistic hypothesis regarding the sensing process, leading to simple sensing models that, despite allowing fast depth estimation from few acquisitions, often ignore relevant considerations for real operation, leaving the door open for systematic errors that affect the final depth accuracy. Typical examples are ignoring the effect of the illumination devices on the final shape of the illumination signal, supposing a sinusoidal reference signal at pixel level, or not accounting for multipath effects. In this work, we present a novel framework for PMD-based signal acquisition and recovery that exploits the sparsity of CW illumination signals in the frequency domain to provide accurate reconstruction of the illumination waveforms as received by the PMD pixels. Our method is extremely robust to signal distortion and noise, since no assumption is made on the illumination signal, other than being a periodic signal. Our approach ensures that no valuable information is lost during the sensing process and allows, therefore, accurate phase shift estimation in a wider range of operation conditions, getting rid of unrealistic assumptions.