PhD forum : multiple camera management using wide base-line matching

Manual calibration of large and dynamic networks of cameras is labour intensive and time consuming. This is a strong motivator for the development of automatic calibration methods. Automatic calibration relies on the ability to find correspondences between multiple views of the same scene. If the cameras are sparsely placed, this can be a very difficult task. This PhD project focuses on the further development of uncalibrated wide baseline matching techniques.

Design and evaluation of an image analysis platform for low-power, low-bandwidth camera networks

We describe the design and evaluation of a platform for networks of cameras in low-bandwidth, low-power sensor networks. In our work to date we have investigated two different DSP hardware/software platforms for undertaking the tasks of compression and object detection and tracking. We compare the relative merits of each of the hardware and software platforms in terms of both performance and energy consumption. Finally we discuss what we believe are the ongoing research questions for image processing in WSNs.

Camera Botanica 1

Camera Botanica 1 - testing a design process (unrealised buildings). ---------- Sited in a highly biodiverse and bushfire prone heathlands on the South-east coast of Western Australia, Camera Botanica 1 is a test of a new design methodology for achieving ecologically sustainable architecture in biodiverse, bushfire prone landscapes. ---------- The design methods were intensively site-based with the author-designer conducting his own site surveys using high-end professional grade surveying equipment such as: Real Time Kinematic GPS (landform survey); Terrestrial laser scanning (vegetation survey); laser levelling and Total Station surveys (erection of scaffolds and contour lines). ---------- This was the first time, internationally, that terrestrial laser scanning was used to measure vegetation. These precise surveys enabled the construction of highly detailed models and drawings - a facility that has not been available prior to this technology. ---------- Designed for a real client and a real site - Camera Botanica 1 is a hypothetical design outcome which demonstrates the efficacy of a new design methodology and thus expands on knowledge of the applicability of new surveying technologies to the design of ecologically sustainable architecture in biodiverse landscapes.

Camera Botanica 2

Camera Botanica 2 - testing a design process (unrealised building). Sited in a highly biodiverse and bushfire prone heathlands on the South-east coast of Western Australia, Camera Botanica 2 is a test of a new design methodology for achieving ecologically sustainable architecture in biodiverse, bushfire prone landscapes. ---------- The design method was intensively site-based with the author-designer conducting his own site surveys using high-end professional grade surveying equipment such as: Real Time Kinematic GPS (landform survey); Terrestrial laser scanning (vegetation survey); laser levelling and Total Station surveys (erection of scaffolds and contour lines). ---------- This was the first time, internationally, that terrestrial laser scanning was used to measure vegetation. These precise surveys enabled the construction of highly detailed models and drawings - a facility that has not been available prior to this technology. ---------- Designed for a real client and a real site - Camera Botanica 2 is a hypothetical design outcome which demonstrates the efficacy of a new design methodology and thus expands on knowledge of the applicability of new surveying technologies to the design of ecologically sustainable architecture in biodiverse landscapes.

Demonstration of image compression in a low-bandwidth wireless camera network

This paper presents an overview of our demonstration of a low-bandwidth, wireless camera network where image compression is undertaken at each node. We briefly introduce the Fleck hardware platform we have developed as well as describe the image compression algorithm which runs on individual nodes. The demo will show real-time image data coming back to base as individual camera nodes are added to the network. Copyright 2007 ACM.

Real-time image streaming over a low-bandwidth wireless camera network

In this paper we describe the recent development of a low-bandwidth wireless camera sensor network. We propose a simple, yet effective, network architecture which allows multiple cameras to be connected to the network and synchronize their communication schedules. Image compression of greater than 90% is performed at each node running on a local DSP coprocessor, resulting in nodes using 1/8th the energy compared to streaming uncompressed images. We briefly introduce the Fleck wireless node and the DSP/camera sensor, and then outline the network architecture and compression algorithm. The system is able to stream color QVGA images over the network to a base station at up to 2 frames per second. © 2007 IEEE.

Mapping a suburb with a single camera using a biologically inspired SLAM system

This paper describes a biologically inspired approach to vision-only simultaneous localization and mapping (SLAM) on ground-based platforms. The core SLAM system, dubbed RatSLAM, is based on computational models of the rodent hippocampus, and is coupled with a lightweight vision system that provides odometry and appearance information. RatSLAM builds a map in an online manner, driving loop closure and relocalization through sequences of familiar visual scenes. Visual ambiguity is managed by maintaining multiple competing vehicle pose estimates, while cumulative errors in odometry are corrected after loop closure by a map correction algorithm. We demonstrate the mapping performance of the system on a 66 km car journey through a complex suburban road network. Using only a web camera operating at 10 Hz, RatSLAM generates a coherent map of the entire environment at real-time speed, correctly closing more than 51 loops of up to 5 km in length.

Featureless vehicle-based visual SLAM with a consumer camera

The Simultaneous Localisation And Mapping (SLAM) problem is one of the major challenges in mobile robotics. Probabilistic techniques using high-end range finding devices are well established in the field, but recent work has investigated vision-only approaches. We present an alternative approach to the leading existing techniques, which extracts approximate rotational and translation velocity information from a vehicle-mounted consumer camera, without tracking landmarks. When coupled with an existing SLAM system, the vision module is able to map a 45 metre long indoor loop and a 1.6 km long outdoor road loop, without any parameter or system adjustment between tests. The work serves as a promising pilot study into ground-based vision-only SLAM, with minimal geometric interpretation of the environment.

Single camera vision-only SLAM on a suburban road network

Simultaneous Localization And Mapping (SLAM) is one of the major challenges in mobile robotics. Probabilistic techniques using high-end range finding devices are well established in the field, but recent work has investigated vision only approaches. This paper presents a method for generating approximate rotational and translation velocity information from a single vehicle-mounted consumer camera, without the computationally expensive process of tracking landmarks. The method is tested by employing it to provide the odometric and visual information for the RatSLAM system while mapping a complex suburban road network. RatSLAM generates a coherent map of the environment during an 18 km long trip through suburban traffic at speeds of up to 60 km/hr. This result demonstrates the potential of ground based vision-only SLAM using low cost sensing and computational hardware.

Multiple camera management using wide baseline matching

Camera calibration information is required in order for multiple camera networks to deliver more than the sum of many single camera systems. Methods exist for manually calibrating cameras with high accuracy. Manually calibrating networks with many cameras is, however, time consuming, expensive and impractical for networks that undergo frequent change. For this reason, automatic calibration techniques have been vigorously researched in recent years. Fully automatic calibration methods depend on the ability to automatically find point correspondences between overlapping views. In typical camera networks, cameras are placed far apart to maximise coverage. This is referred to as a wide base-line scenario. Finding sufficient correspondences for camera calibration in wide base-line scenarios presents a significant challenge. This thesis focuses on developing more effective and efficient techniques for finding correspondences in uncalibrated, wide baseline, multiple-camera scenarios. The project consists of two major areas of work. The first is the development of more effective and efficient view covariant local feature extractors. The second area involves finding methods to extract scene information using the information contained in a limited set of matched affine features. Several novel affine adaptation techniques for salient features have been developed. A method is presented for efficiently computing the discrete scale space primal sketch of local image features. A scale selection method was implemented that makes use of the primal sketch. The primal sketch-based scale selection method has several advantages over the existing methods. It allows greater freedom in how the scale space is sampled, enables more accurate scale selection, is more effective at combining different functions for spatial position and scale selection, and leads to greater computational efficiency. Existing affine adaptation methods make use of the second moment matrix to estimate the local affine shape of local image features. In this thesis, it is shown that the Hessian matrix can be used in a similar way to estimate local feature shape. The Hessian matrix is effective for estimating the shape of blob-like structures, but is less effective for corner structures. It is simpler to compute than the second moment matrix, leading to a significant reduction in computational cost. A wide baseline dense correspondence extraction system, called WiDense, is presented in this thesis. It allows the extraction of large numbers of additional accurate correspondences, given only a few initial putative correspondences. It consists of the following algorithms: An affine region alignment algorithm that ensures accurate alignment between matched features; A method for extracting more matches in the vicinity of a matched pair of affine features, using the alignment information contained in the match; An algorithm for extracting large numbers of highly accurate point correspondences from an aligned pair of feature regions. Experiments show that the correspondences generated by the WiDense system improves the success rate of computing the epipolar geometry of very widely separated views. This new method is successful in many cases where the features produced by the best wide baseline matching algorithms are insufficient for computing the scene geometry.

Investigating the hydrodynamic performance of a gross pollutant trap

Field studies show that the internal screens in a gross pollutant trap (GPT) are often clogged with organic matter, due to infrequent cleaning. The hydrodynamic performance of a GPT with fully blocked screens was comprehensively investigated under a typical range of onsite operating conditions. Using an acoustic Doppler velocimeter (ADV), velocity profiles across three critical sections of the GPT were measured and integrated to examine the net fluid flow at each section. The data revealed that when the screens are fully blocked, the flow structure within the GPT radically changes. Consequently, the capture/retention performance of the device rapidly deteriorates. Good agreement was achieved between the experimental and the previous 2D computational fluid dynamics (CFD) velocity profiles for the lower GPT inlet flow conditions.

The capture/retention investigation of a gross pollutant trap

A technique was developed to investigate the capture/retention characteristic of a gross pollutant trap (GPT) with fully and partially blocked internal screens. Custom modified spheres of variable density filled with liquid were released into the GPT inlet and monitored at the outlet. The outlet data shows that the capture/retention performances of a GPT with fully blocked screens deteriorate rapidly. During higher flow rates, screen blockages below 68% approach maximum efficiency. At lower flow rates, the high performance trend is reversed and the variation in behaviour of pollutants with different densities becomes more noticeable. Additional experiments with a second upstream inlet configured GPT showed an improved capture/retention performance. It was also noted that the bypass allows the incoming pollutants to escape when the GPT is blocked. This useful feature prevents upstream blockages between cleaning intervals.

Camera calibration in wireless multimedia sensor networks

Wireless Multi-media Sensor Networks (WMSNs) have become increasingly popular in recent years, driven in part by the increasing commoditization of small, low-cost CMOS sensors. As such, the challenge of automatically calibrating these types of cameras nodes has become an important research problem, especially for the case when a large quantity of these type of devices are deployed. This paper presents a method for automatically calibrating a wireless camera node with the ability to rotate around one axis. The method involves capturing images as the camera is rotated and computing the homographies between the images. The camera parameters, including focal length, principal point and the angle and axis of rotation can then recovered from two or more homographies. The homography computation algorithm is designed to deal with the limited resources of the wireless sensor and to minimize energy con- sumption. In this paper, a modified RANdom SAmple Consensus (RANSAC) algorithm is proposed to effectively increase the efficiency and reliability of the calibration procedure.