Visual metrics for the evaluation of sensor data quality in outdoor perception

This paper proposes an experimental study of quality metrics that can be applied to visual and infrared images acquired from cameras onboard an unmanned ground vehicle (UGV). The relevance of existing metrics in this context is discussed and a novel metric is introduced. Selected metrics are evaluated on data collected by a UGV in clear and challenging environmental conditions, represented in this paper by the presence of airborne dust or smoke. An example of application is given with monocular SLAM estimating the pose of the UGV while smoke is present in the environment. It is shown that the proposed novel quality metric can be used to anticipate situations where the quality of the pose estimate will be significantly degraded due to the input image data. This leads to decisions of advantageously switching between data sources (e.g. using infrared images instead of visual images).

Visual metrics for the evaluation of sensor data quality in outdoor perception

This paper proposes an experimental study of quality metrics that can be applied to visual and infrared images acquired from cameras onboard an unmanned ground vehicle (UGV). The relevance of existing metrics in this context is discussed and a novel metric is introduced. Selected metrics are evaluated on data collected by a UGV in clear and challenging environmental conditions, represented in this paper by the presence of airborne dust or smoke.

Datasets for the evaluation of multi-sensor perception in natural environments with challenging conditions

This paper presents large, accurately calibrated and time-synchronised datasets, gathered outdoors in controlled environmental conditions, using an unmanned ground vehicle (UGV), equipped with a wide variety of sensors. It discusses how the data collection process was designed, the conditions in which these datasets have been gathered, and some possible outcomes of their exploitation, in particular for the evaluation of performance of sensors and perception algorithms for UGVs.

Sensor Data Integrity : Multi-Sensor Perception for Unmanned Ground Vehicles

This document describes large, accurately calibrated and time-synchronised datasets, gathered in controlled environmental conditions, using an unmanned ground vehicle equipped with a wide variety of sensors. These sensors include: multiple laser scanners, a millimetre wave radar scanner, a colour camera and an infra-red camera. Full details of the sensors are given, as well as the calibration parameters needed to locate them with respect to each other and to the platform. This report also specifies the format and content of the data, and the conditions in which the data have been gathered. The data collection was made in two different situations of the vehicle: static and dynamic. The static tests consisted of sensing a fixed ’reference’ terrain, containing simple known objects, from a motionless vehicle. For the dynamic tests, data were acquired from a moving vehicle in various environments, mainly rural, including an open area, a semi-urban zone and a natural area with different types of vegetation. For both categories, data have been gathered in controlled environmental conditions, which included the presence of dust, smoke and rain. Most of the environments involved were static, except for a few specific datasets which involve the presence of a walking pedestrian. Finally, this document presents illustrations of the effects of adverse environmental conditions on sensor data, as a first step towards reliability and integrity in autonomous perceptual systems.

Combining multiple sensor modalities for a localisation robust to smoke

This paper proposes an approach to obtain a localisation that is robust to smoke by exploiting multiple sensing modalities: visual and infrared (IR) cameras. This localisation is based on a state-of-the-art visual SLAM algorithm. First, we show that a reasonably accurate localisation can be obtained in the presence of smoke by using only an IR camera, a sensor that is hardly affected by smoke, contrary to a visual camera (operating in the visible spectrum). Second, we demonstrate that improved results can be obtained by combining the information from the two sensor modalities (visual and IR cameras). Third, we show that by detecting the impact of smoke on the visual images using a data quality metric, we can anticipate and mitigate the degradation in performance of the localisation by discarding the most affected data. The experimental validation presents multiple trajectories estimated by the various methods considered, all thoroughly compared to an accurate dGPS/INS reference.

The Marulan data sets: multi-sensor perception in a natural environment with challenging conditions

In this paper we present large, accurately calibrated and time-synchronized data sets, gathered outdoors in controlled and variable environmental conditions, using an unmanned ground vehicle (UGV), equipped with a wide variety of sensors. These include four 2D laser scanners, a radar scanner, a color camera and an infrared camera. It provides a full description of the system used for data collection and the types of environments and conditions in which these data sets have been gathered, which include the presence of airborne dust, smoke and rain.

Local inter-session variability modelling for object classification

Object classification is plagued by the issue of session variation. Session variation describes any variation that makes one instance of an object look different to another, for instance due to pose or illumination variation. Recent work in the challenging task of face verification has shown that session variability modelling provides a mechanism to overcome some of these limitations. However, for computer vision purposes, it has only been applied in the limited setting of face verification. In this paper we propose a local region based intersession variability (ISV) modelling approach, and apply it to challenging real-world data. We propose a region based session variability modelling approach so that local session variations can be modelled, termed Local ISV. We then demonstrate the efficacy of this technique on a challenging real-world fish image database which includes images taken underwater, providing significant real-world session variations. This Local ISV approach provides a relative performance improvement of, on average, 23% on the challenging MOBIO, Multi-PIE and SCface face databases. It also provides a relative performance improvement of 35% on our challenging fish image dataset.

Carbon nanotube composite sensor for structural health monitoring of bridge structures

Bridges are important infrastructures of all nations and are required for transportation of goods as well as human. A catastrophic failure can result in loss of lives and enormous financial hardship to the nation. Although various kinds of sensors are now available to monitor the health of the structures due to corrosion, they do not provide permanent and long term measurements. This paper investigates the fabrication of Carbon Nanotube (CNT) based composite sensors for corrosion detection of structures. Multi-wall CNT (MWCNT)/Nafion composite sensors were fabricated to evaluate their electrical properties for corrosion detection. The test specimens were subjected to real life corrosion experimental tests and the results confirm that the electrical resistance of the sensor electrode was dramatically changed due to corrosion.

Cell image classification using histograms, higher order statistics and adaboost

A cell classification algorithm that uses first, second and third order statistics of pixel intensity distributions over pre-defined regions is implemented and evaluated. A cell image is segmented into 6 regions extending from a boundary layer to an inner circle. First, second and third order statistical features are extracted from histograms of pixel intensities in these regions. Third order statistical features used are one-dimensional bispectral invariants. 108 features were considered as candidates for Adaboost based fusion. The best 10 stage fused classifier was selected for each class and a decision tree constructed for the 6-class problem. The classifier is robust, accurate and fast by design.

Real-time image classification for adaptive mission planning using an Autonomous Underwater Vehicle

Real-time image analysis and classification onboard robotic marine vehicles, such as AUVs, is a key step in the realisation of adaptive mission planning for large-scale habitat mapping in previously unexplored environments. This paper describes a novel technique to train, process, and classify images collected onboard an AUV used in relatively shallow waters with poor visibility and non-uniform lighting. The approach utilises Förstner feature detectors and Laws texture energy masks for image characterisation, and a bag of words approach for feature recognition. To improve classification performance we propose a usefulness gain to learn the importance of each histogram component for each class. Experimental results illustrate the performance of the system in characterisation of a variety of marine habitats and its ability to operate onboard an AUV's main processor suitable for real-time mission planning.

Sensor Network Based AUV Localisation

The operation of Autonomous Underwater Vehicles (AUVs) within underwater sensor network fields provides an opportunity to reuse the network infrastructure for long baseline localisation of the AUV. Computationally efficient localisation can be accomplished using off-the-shelf hardware that is comparatively inexpensive and which could already be deployed in the environment for monitoring purposes. This paper describes the development of a particle filter based localisation system which is implemented onboard an AUV in real-time using ranging information obtained from an ad-hoc underwater sensor network. An experimental demonstration of this approach was conducted in a lake with results presented illustrating network communication and localisation performance.

The impact of OCR accuracy on automated cancer classification of pathology reports

Objective To evaluate the effects of Optical Character Recognition (OCR) on the automatic cancer classification of pathology reports. Method Scanned images of pathology reports were converted to electronic free-text using a commercial OCR system. A state-of-the-art cancer classification system, the Medical Text Extraction (MEDTEX) system, was used to automatically classify the OCR reports. Classifications produced by MEDTEX on the OCR versions of the reports were compared with the classification from a human amended version of the OCR reports. Results The employed OCR system was found to recognise scanned pathology reports with up to 99.12% character accuracy and up to 98.95% word accuracy. Errors in the OCR processing were found to minimally impact on the automatic classification of scanned pathology reports into notifiable groups. However, the impact of OCR errors is not negligible when considering the extraction of cancer notification items, such as primary site, histological type, etc. Conclusions The automatic cancer classification system used in this work, MEDTEX, has proven to be robust to errors produced by the acquisition of freetext pathology reports from scanned images through OCR software. However, issues emerge when considering the extraction of cancer notification items.

Classification of pathology reports for cancer registry notifications

Objective: To develop a system for the automatic classification of pathology reports for Cancer Registry notifications. Method: A two pass approach is proposed to classify whether pathology reports are cancer notifiable or not. The first pass queries pathology HL7 messages for known report types that are received by the Queensland Cancer Registry (QCR), while the second pass aims to analyse the free text reports and identify those that are cancer notifiable. Cancer Registry business rules, natural language processing and symbolic reasoning using the SNOMED CT ontology were adopted in the system. Results: The system was developed on a corpus of 500 histology and cytology reports (with 47% notifiable reports) and evaluated on an independent set of 479 reports (with 52% notifiable reports). Results show that the system can reliably classify cancer notifiable reports with a sensitivity, specificity, and positive predicted value (PPV) of 0.99, 0.95, and 0.95, respectively for the development set, and 0.98, 0.96, and 0.96 for the evaluation set. High sensitivity can be achieved at a slight expense in specificity and PPV. Conclusion: The system demonstrates how medical free-text processing enables the classification of cancer notifiable pathology reports with high reliability for potential use by Cancer Registries and pathology laboratories.