Long exposure localization in darkness using consumer cameras

In this paper we demonstrate passive vision-based localization in environments more than two orders of magnitude darker than the current benchmark using a 100 webcam and a 500 camera. Our approach uses the camera’s maximum exposure duration and sensor gain to achieve appropriately exposed images even in unlit night-time environments, albeit with extreme levels of motion blur. Using the SeqSLAM algorithm, we first evaluate the effect of variable motion blur caused by simulated exposures of 132 ms to 10000 ms duration on localization performance. We then use actual long exposure camera datasets to demonstrate day-night localization in two different environments. Finally we perform a statistical analysis that compares the baseline performance of matching unprocessed greyscale images to using patch normalization and local neighbourhood normalization – the two key SeqSLAM components. Our results and analysis show for the first time why the SeqSLAM algorithm is effective, and demonstrate the potential for cheap camera-based localization systems that function across extreme perceptual change.

Scene invariant multi camera crowd counting

Automated crowd counting has become an active field of computer vision research in recent years. Existing approaches are scene-specific, as they are designed to operate in the single camera viewpoint that was used to train the system. Real world camera networks often span multiple viewpoints within a facility, including many regions of overlap. This paper proposes a novel scene invariant crowd counting algorithm that is designed to operate across multiple cameras. The approach uses camera calibration to normalise features between viewpoints and to compensate for regions of overlap. This compensation is performed by constructing an 'overlap map' which provides a measure of how much an object at one location is visible within other viewpoints. An investigation into the suitability of various feature types and regression models for scene invariant crowd counting is also conducted. The features investigated include object size, shape, edges and keypoints. The regression models evaluated include neural networks, K-nearest neighbours, linear and Gaussian process regresion. Our experiments demonstrate that accurate crowd counting was achieved across seven benchmark datasets, with optimal performance observed when all features were used and when Gaussian process regression was used. The combination of scene invariance and multi camera crowd counting is evaluated by training the system on footage obtained from the QUT camera network and testing it on three cameras from the PETS 2009 database. Highly accurate crowd counting was observed with a mean relative error of less than 10%. Our approach enables a pre-trained system to be deployed on a new environment without any additional training, bringing the field one step closer toward a 'plug and play' system.

Sensing place : embodiment, sensoriality, kinesis, and children behind the camera

This article is a call to literacy teachers and researchers to embrace the possibility of attending more consciously to the senses in digital media production. Literacy practices do not occur only in the mind, but involve the sensoriality, embodiment, co-presence, and movement of bodies. This paper theorises the sensorial and embodied dimension of children’s filmmaking about place in two communities in Australia. The films were created by pre-teen Indigenous and non-Indigenous children in Logan, Queensland, and by Indigenous teenagers at the Warralong campus of the Strelley Community School in remote Western Australia. The films were created through engagement in cross-curricular units that sensitised the students’ experience of local places, gathering corporeal information through their sensing bodies as they interacted with the local ecology. The analysis highlights how the sensorial and bodily nature of literacy practice through documentary filmmaking was central to the children’s formation and representation of knowledge, because knowledge and literacy practices are not only acquired through the mind, but are also reliant on embodiment, sensoriality, co-presence, and kinesics of the body in place.

Innovations in dietary interventions : Use of a photographic food diary method and telephone linked computerized care in chronic disease

Access to dietetic care is important in chronic disease management and innovative technologies assists in this purpose. Photographic dietary records (PhDR) using mobile phones or cameras are valid and convenient for patients. Innovations in providing dietary interventions via telephone and computer can also inform dietetic practice. Three studies are presented. A mobile phone method was validated by comparing energy intake (EI) to a weighed food record and a measure of energy expenditure (EE) obtained using the doubly labelled water technique in 10 adults with T2 diabetes. The level of agreement between mean (±sd) energy intake mobile phone (8.2±1.7 MJ) and weighed record (8.5±1.6 MJ) was high (p=0.392), however EI/EE for both methods gave similar levels of under-reporting (0.69 and 0.72). All subjects preferred using the mobile phone vs. weighed record. Nineteen individuals with Parkinsons disease kept 3-day PhDRs on three occasions using point-and-shoot digital cameras over a 12 week period. The camera was rated as easy to use by 89%, keeping a PhDR was considered acceptable by 94% and none would rather use a “pen and paper” method. Eighty-three percent felt confident to use the camera again to record intake. An interactive, automated telephone system designed to coach people with T2 diabetes to adopt and maintain diabetes self-care behaviours, including nutrition, showed trends for improvements in total fat, saturated fat and vegetable intake of the intervention group compared to control participants over 6 months. Innovative technologies are acceptable to patients with chronic conditions and can be incorporated into dietetic care.

Selective combination of visual and thermal imaging for resilient localization in adverse conditions : day and night, smoke and fire

Long-term autonomy in robotics requires perception systems that are resilient to unusual but realistic conditions that will eventually occur during extended missions. For example, unmanned ground vehicles (UGVs) need to be capable of operating safely in adverse and low-visibility conditions, such as at night or in the presence of smoke. The key to a resilient UGV perception system lies in the use of multiple sensor modalities, e.g., operating at different frequencies of the electromagnetic spectrum, to compensate for the limitations of a single sensor type. In this paper, visual and infrared imaging are combined in a Visual-SLAM algorithm to achieve localization. We propose to evaluate the quality of data provided by each sensor modality prior to data combination. This evaluation is used to discard low-quality data, i.e., data most likely to induce large localization errors. In this way, perceptual failures are anticipated and mitigated. An extensive experimental evaluation is conducted on data sets collected with a UGV in a range of environments and adverse conditions, including the presence of smoke (obstructing the visual camera), fire, extreme heat (saturating the infrared camera), low-light conditions (dusk), and at night with sudden variations of artificial light. A total of 240 trajectory estimates are obtained using five different variations of data sources and data combination strategies in the localization method. In particular, the proposed approach for selective data combination is compared to methods using a single sensor type or combining both modalities without preselection. We show that the proposed framework allows for camera-based localization resilient to a large range of low-visibility conditions.

Reliable automatic camera-laser calibration

Camera-laser calibration is necessary for many robotics and computer vision applications. However, existing calibration toolboxes still require laborious effort from the operator in order to achieve reliable and accurate results. This paper proposes algorithms that augment two existing trustful calibration methods with an automatic extraction of the calibration object from the sensor data. The result is a complete procedure that allows for automatic camera-laser calibration. The first stage of the procedure is automatic camera calibration which is useful in its own right for many applications. The chessboard extraction algorithm it provides is shown to outperform openly available techniques. The second stage completes the procedure by providing automatic camera-laser calibration. The procedure has been verified by extensive experimental tests with the proposed algorithms providing a major reduction in time required from an operator in comparison to manual methods.

Towards discrimination of challenging conditions for UGVs with visual and infrared sensors

This work aims to contribute to reliability and integrity in perceptual systems of autonomous ground vehicles. Information theoretic based metrics to evaluate the quality of sensor data are proposed and applied to visual and infrared camera images. The contribution of the proposed metrics to the discrimination of challenging conditions is discussed and illustrated with the presence of airborne dust and smoke.

Locating people in video from semantic descriptions : a new database and approach

The location of previously unseen and unregistered individuals in complex camera networks from semantic descriptions is a time consuming and often inaccurate process carried out by human operators, or security staff on the ground. To promote the development and evaluation of automated semantic description based localisation systems, we present a new, publicly available, unconstrained 110 sequence database, collected from 6 stationary cameras. Each sequence contains detailed semantic information for a single search subject who appears in the clip (gender, age, height, build, hair and skin colour, clothing type, texture and colour), and between 21 and 290 frames for each clip are annotated with the target subject location (over 11,000 frames are annotated in total). A novel approach for localising a person given a semantic query is also proposed and demonstrated on this database. The proposed approach incorporates clothing colour and type (for clothing worn below the waist), as well as height and build to detect people. A method to assess the quality of candidate regions, as well as a symmetry driven approach to aid in modelling clothing on the lower half of the body, is proposed within this approach. An evaluation on the proposed dataset shows that a relative improvement in localisation accuracy of up to 21 is achieved over the baseline technique.

Technicolouring the fridge : reducing food waste through uses of colour-coding and cameras

Domestic food wastage is a growing problem for the environment and food security. Some causes of domestic food wastes are attributed to a consumer’s behaviours during food purchasing, storage and consumption, such as: excessive food purchases and stockpiling in storage. Recent efforts in human-computer interaction research have examined ways of influencing consumer behaviour. The outcomes have led to a number of interventions that assist users with performing everyday tasks. The Internet Fridge is an example of such an intervention. However, new pioneering technologies frequently confront barriers that restrict their future impact in the market place, which has prompted investigations into the effectiveness of behaviour changing interventions used to encourage more sustainable practices. In this paper, we investigate and compare the effectiveness of two interventions that encourage behaviour change: FridgeCam and the Colour Code Project. We use FridgeCam to examine how improving a consumer’s food supply knowledge can reduce food stockpiling. We use the Colour Code Project to examine how improving consumer awareness of food location can encourage consumption of forgotten foods. We explore opportunities to integrate these interventions into commercially available technologies, such as the Internet Fridge, to: (i) increase the technology’s benefit and value to users, and (ii) promote reduced domestic food wastage. We conclude that interventions improving consumer food supply and location knowledge can promote behaviours that reduce domestic food waste over a longer term. The implications of this research present new opportunities for existing and future technologies to play a key role in reducing domestic food waste.

Towards Vision-Based Pose- and Condition-Invariant Place Recognition along Routes

Vision-based place recognition involves recognising familiar places despite changes in environmental conditions or camera viewpoint (pose). Existing training-free methods exhibit excellent invariance to either of these challenges, but not both simultaneously. In this paper, we present a technique for condition-invariant place recognition across large lateral platform pose variance for vehicles or robots travelling along routes. Our approach combines sideways facing cameras with a new multi-scale image comparison technique that generates synthetic views for input into the condition-invariant Sequence Matching Across Route Traversals (SMART) algorithm. We evaluate the system’s performance on multi-lane roads in two different environments across day-night cycles. In the extreme case of day-night place recognition across the entire width of a four-lane-plus-median-strip highway, we demonstrate performance of up to 44% recall at 100% precision, where current state-of-the-art fails.

Children's emotions and multimodal appraisal of places : walking with the camera

This sensory ethnography explores the affordances and constraints of multimodal design to represent emotions and appraisal associated with experiencing local places. Digital video production, walking with the camera, and the use of a think-aloud protocol to reflect on the videos, provided an opportunity for the primary school children to represent their emotions and appraisal of places multimodally. Applying a typology from Martin and White's (2005) framework for the Language of Evaluation, children's multimodal emotional responses to places in this study tended toward happiness, security, and satisfaction. The findings demonstrate an explicit connection between children's emotions in response to local places through video, while highlighting the potential for teachers to use digital filmmaking to allow children to reflect actively on their placed experiences and represent their emotional reactions to places through multiple modes.

Now we can “see the forest and the trees too” but there are risks : Camera trapping and privacy law in Australia

The use of camera traps in wildlife management is an increasingly common practice. A phenomenon which is also becoming more common is for such camera traps to unintentionally film individuals engaged in a variety of activities, ranging from the innocent to the nefarious and including lewd or potentially embarrassing behaviour. It is therefore possible for the use of camera traps to accidentally encroach upon the privacy rights of persons who venture into the area of surveillance. In this chapter we describe the legal framework of privacy in Australia and discuss the potential risk of this sleeping tiger for users of camera traps. We also present the results of a survey of camera trap users to assess the frequency of such unintended captures and the nature of activity being filmed before discussing the practical implications of these laws for camera traps users in this country and make recommendations.

Automatic camera exposure control

It is commonplace to use digital video cameras in robotic applications. These cameras have built-in exposure control but they do not have any knowledge of the environment, the lens being used, the important areas of the image and do not always produce optimal image exposure. Therefore, it is desirable and often necessary to control the exposure off the camera. In this paper we present a scheme for exposure control which enables the user application to determine the area of interest. The proposed scheme introduces an intermediate transparent layer between the camera and the user application which combines the information from these for optimal exposure production. We present results from indoor and outdoor scenarios using directional and fish-eye lenses showing the performance and advantages of this framework.

Large scale monitoring of crowds and building utilisation: A new database and distributed approach

Public buildings and large infrastructure are typically monitored by tens or hundreds of cameras, all capturing different physical spaces and observing different types of interactions and behaviours. However to date, in large part due to limited data availability, crowd monitoring and operational surveillance research has focused on single camera scenarios which are not representative of real-world applications. In this paper we present a new, publicly available database for large scale crowd surveillance. Footage from 12 cameras for a full work day covering the main floor of a busy university campus building, including an internal and external foyer, elevator foyers, and the main external approach are provided; alongside annotation for crowd counting (single or multi-camera) and pedestrian flow analysis for 10 and 6 sites respectively. We describe how this large dataset can be used to perform distributed monitoring of building utilisation, and demonstrate the potential of this dataset to understand and learn the relationship between different areas of a building.

Report on Red Light Camera Program: Operation from July 1988 to December 1989

EXECUTIVE SUMMARY (excerpts) The red light camera (RLC) program commenced in July 1988, with five cameras operating at 15 sites in metropolitan Adelaide. This report deals with the first eighteen months of operation, to December 1989. A number of recommendations have been made… PROGRAM EVALUATION … In 1989 dollars, the program was estimated to have achieved an accident reduction benefit of $1.4m in the first 12 months of operation, which is almost twice the benefit expected using the assumptions made when selecting the sites. (There are 8 recommendations, mostly specific to the particular program characteristics)