Identification of moving obstacles with pyramidal Lucas Kanade optical flow and k means clustering

This paper describes the methodology for identifying moving obstacles by obtaining a reliable and a sparse optical flow from image sequences. Given a sequence of images, basically we can detect two-types of on road vehicles, vehicles traveling in the opposite direction and vehicles traveling in the same direction. For both types, distinct feature points can be detected by Shi and Tomasi corner detector algorithm. Then pyramidal Lucas Kanade method for optical flow calculation is used to match the sparse feature set of one frame on the consecutive frame. By applying k means clustering on four component feature vector, which are to be the coordinates of the feature point and the two components of the optical flow, we can easily calculate the centroids of the clusters and the objects can be easily tracked. The vehicles traveling in the opposite direction produce a diverging vector field, while vehicles traveling in the same direction produce a converging vector field

Metrics to assess ecological condition, change, and impacts in sandy beach ecosystems

Complexity is increasingly the hallmark in environmental management practices of sandy shorelines. This arises primarily from meeting growing public demands (e.g., real estate, recreation) whilst reconciling economic demands with expectations of coastal users who have modern conservation ethics. Ideally, shoreline management is underpinned by empirical data, but selecting ecologically-meaningful metrics to accurately measure the condition of systems, and the ecological effects of human activities, is a complex task. Here we construct a framework for metric selection, considering six categories of issues that authorities commonly address: erosion; habitat loss; recreation; fishing; pollution (litter and chemical contaminants); and wildlife conservation. Possible metrics were scored in terms of their ability to reflect environmental change, and against criteria that are widely used for judging the performance of ecological indicators (i.e., sensitivity, practicability, costs, and public appeal). From this analysis, four types of broadly applicable metrics that also performed very well against the indicator criteria emerged: 1.) traits of bird populations and assemblages (e.g., abundance, diversity, distributions, habitat use); 2.) breeding/reproductive performance sensu lato (especially relevant for birds and turtles nesting on beaches and in dunes, but equally applicable to invertebrates and plants); 3.) population parameters and distributions of vertebrates associated primarily with dunes and the supralittoral beach zone (traditionally focused on birds and turtles, but expandable to mammals); 4.) compound measurements of the abundance/cover/biomass of biota (plants, invertebrates, vertebrates) at both the population and assemblage level. Local constraints (i.e., the absence of birds in highly degraded urban settings or lack of dunes on bluff-backed beaches) and particular issues may require alternatives. Metrics - if selected and applied correctly - provide empirical evidence of environmental condition and change, but often do not reflect deeper environmental values per se. Yet, values remain poorly articulated for many beach systems; this calls for a comprehensive identification of environmental values and the development of targeted programs to conserve these values on sandy shorelines globally.

Re-framing values for a World Heritage future: what type of icon will K'gari-Fraser Island become?

K’gari-Fraser Island, the world's largest barrier sand island, is at the crossroads of World Heritage status, due to destructive environmental use in concert with climate change. Will K’gari-Fraser Island exemplify innovative, adaptive management or become just another degraded recreational facility? We synthesize the likely impact of human pressures and predicted consequences on the values of this island. World-renown natural beauty and ongoing biological and geological processes in coastal, wetland, heathland and rainforest environments, all contribute to its World Heritage status. The impact of hundreds of thousands of annual visitors is increasing on the island's biodiversity, cultural connections, ecological functions and environmental values. Maintaining World Heritage values will necessitate the re-framing of values to integrate socioeconomic factors in management and reduce extractive forms of tourism. Environmentally sound, systematic conservation planning that achieves social equity is urgently needed to rectify historical mistakes and update current management practices. Characterizing and sustaining biological refugia will be important to retain biodiversity in areas that are less visited. The development of a coherent approach to interpretation concerning history, access and values is required to encourage a more sympathetic use of this World Heritage environment. Alternatively, ongoing attrition of the islands values by increased levels of destructive use is inevitable.

Human threats to sandy beaches: a meta-analysis of ghost crabs illustrates global anthropogenic impacts

Beach and coastal dune systems are increasingly subjected to a broad range of anthropogenic pressures that on many shorelines require significant conservation and mitigation interventions. But these interventions require reliable data on the severity and frequency of adverse ecological impacts. Such evidence is often obtained by measuring the response of 'indicator species'.Ghost crabs are the largest invertebrates inhabiting tropical and subtropical sandy shores and are frequently used to assess human impacts on ocean beaches. Here we present the first global meta-analysis of these impacts, and analyse the design properties and metrics of studies using ghost-crabs in their assessment. This was complemented by a gap analysis to identify thematic areas of anthropogenic pressures on sandy beach ecosystems that are under-represented in the published literature.Our meta-analysis demonstrates a broad geographic reach, encompassing studies on shores of the Pacific, Indian, and Atlantic Oceans, as well as the South China Sea. It also reveals what are, arguably, two major limitations: i) the near-universal use of proxies (i.e. burrow counts to estimate abundance) at the cost of directly measuring biological traits and bio-markers in the organism itself; and ii) descriptive or correlative study designs that rarely extend beyond a simple 'compare and contrast approach', and hence fail to identify the mechanistic cause(s) of observed contrasts.Evidence for a historically narrow range of assessed pressures (i.e., chiefly urbanisation, vehicles, beach nourishment, and recreation) is juxtaposed with rich opportunities for the broader integration of ghost crabs as a model taxon in studies of disturbance and impact assessments on ocean beaches. Tangible advances will most likely occur where ghost crabs provide foci for experiments that test specific hypotheses associated with effects of chemical, light and acoustic pollution, as well as the consequences of climate change (e.g. species range shifts).

The early shorebird will catch fewer invertebrates on trampled sandy beaches

Many species of birds breeding on ocean beaches and in coastal dunes are of global conservation concern. Most of these species rely on invertebrates (e.g. insects, small crustaceans) as an irreplaceable food source, foraging primarily around the strandline on the upper beach near the dunes. Sandy beaches are also prime sites for human recreation, which impacts these food resources via negative trampling effects. We quantified acute trampling impacts on assemblages of upper shore invertebrates in a controlled experiment over a range of foot traffic intensities (up to 56 steps per square metre) on a temperate beach in Victoria, Australia. Trampling significantly altered assemblage structure (species composition and density) and was correlated with significant declines in invertebrate abundance and species richness. Trampling effects were strongest for rare species. In heavily trafficked plots the abundance of sand hoppers (Amphipoda), a principal prey item of threatened Hooded Plovers breeding on this beach, was halved. In contrast to the consistently strong effects of trampling, natural habitat attributes (e.g. sediment grain size, compactness) were much less influential predictors. If acute suppression of invertebrates caused by trampling, as demonstrated here, is more widespread on beaches it may constitute a significant threat to endangered vertebrates reliant on these invertebrates. This calls for a re-thinking of conservation actions by considering active management of food resources, possibly through enhancement of wrack or direct augmentation of prey items to breeding territories.

At home on the road? Can drivers' relationships with their cars be associated with territoriality?

The current research explores the relationship between people and their cars within the framework of Altman's theory of human territoriality. It further develops the research of Sandqvist by examining the descriptions given by people with differing ownership and uses of their cars and exploring the congruence between these and the characteristics used to describe human territories. Thirteen focus groups were held with young drivers between the ages of 18 and 25 years, drivers over the age of 25 who are parents of pre-license age children, drivers over the age of 25 who do not regularly transport children, and drivers of work vehicles. Analyses of discussions revealed that drivers’ descriptions of the relationship with their car could be matched with Brown and Altman's descriptions of territory types. However, variations existed both between and within individuals as to the application of the labels ‘primary’, ‘secondary’ and ‘public’ territory to the car. Implications for the understanding of road user behaviour and the further development of theory on the car as a place or an object in terms of territoriality are discussed.

Visual tracking of vehicles using multiresolution analysis and neural network

This paper describes the procedure for detection and tracking of a vehicle from an on-road image sequence taken by a monocular video capturing device in real time. The main objective of such a visual tracking system is to closely follow objects in each frame of a video stream, such that the object position as well as other geometric information are always known. In the tracking system described, the video capturing device is also moving. It is a challenge to detect and track a moving vehicle under a constantly changing environment coupled to real time video processing. The system suggested is robust to implement under different illuminating conditions by using the monocular video capturing device. The vehicle tracking algorithm is one of the most important modules in an autonomous vehicle system, not only it should be very accurate but also must have the safety of other vehicles, pedestrians, and the moving vehicle itself. In order to achieve this an algorithm of multi resolution technique based on Haar basis functions were used for the wavelet transform, where a combination of classification was carried out with the multilayer feed forward neural network. The classification is done in a reduced dimensional space, where principle component analysis (PCA) dimensional reduction technique has been applied to make the classification process much more efficient. The results show the effectiveness of the proposed methodology.

Detection of vehicles with monolithic classifier vis-à-vis a boosted cascaded classifier

This paper describes the comparison of accuracy and performance of two machine learning approaches for visual object detection and tracking vehicles, from an on-road image sequence. The first is a neural network based approach. Where an algorithm of multi resolution technique based on Haar basis functions was used to obtain an image with different scales. Thereafter a classification was carried out with the multilayer feed forward neural network. Principle Component Analysis (PCA) technique was used as a dimension reduction technique to make the classification process much more efficient. The second approach is based on boosting which also yields very good detection rates. In general, boosting is one of the most important developments in classification methodology. It works by sequentially applying a classification algorithm to reweighed versions of the training data, followed by taking a weighted majority vote of the sequence of classifiers thus produced. For this work, a strong classifier was trained by the adaboost algorithm. The results of comparing the two methodologies visà-vis shows the effectiveness of the methods that have been used.

A study on look-ahead control and energy management strategies in hybrid electric vehicles

Fuel efficiency in a hybrid electric vehicle requires a fine balance between usage of combustion engine and battery power. Information about the geometry of the road and traffic ahead can have a great impact on optimized control and the power split between the main parts of a hybrid electric vehicle. This paper provides a survey on the existing methods of control and energy management emphasizing on those that consider the look-ahead road situation and trajectory information. Then it presents the future trends in the control and energy management of hybrid electric vehicles.

A look-ahead road grade determination method for HEVs

This paper presents a look-ahead road grade determination method for use in energy management of hybrid electric vehicles. Data that is gathered from a digital map and vehicle sensors is used to predict the future road grade and longitudinal forces. The predicted information is employed to specify the near future traction force demand. A simulation is carried out using data associated with a 50 km section of a real highway for a typical vehicle. The results are presented and discussed.

Adaptive cruise control look-ahead system for energy management of vehicles

Cruise control in motor vehicles enhances safe and efficient driving by maintaining a constant speed at a preset level. Adaptive Cruise Control (ACC) is the latest development in cruise control. It controls engine throttle position and braking to maintain a safe distance behind a vehicle in front by responding to the speed of this vehicle, thus providing a safer and more relaxing driving environment. ACC can be further developed by including the look-ahead method of predicting environmental factors such as wind speed and road slope. The conventional analytical control methods for adaptive cruise control can generate good results; however they are difficult to design and computationally expensive. In order to achieve a robust, less computationally expensive, and at the same time more natural human-like speed control, intelligent control techniques can be used. This paper presents an Adaptive Neuro-Fuzzy Inference System (ANFIS) based on ACC systems that reduces the energy consumption of the vehicle and improves its efficiency. The Adaptive Cruise Control Look-Ahead (ACC-LA) system works as follows: It calculates the energy consumption of the vehicle under combined dynamic loads like wind drag, slope, kinetic energy and rolling friction using road data, and it includes a look-ahead strategy to predict the future road slope. The cruise control system adaptively controls the vehicle speed based on the preset speed and the predicted future slope information. By using the ANFIS method, the ACC-LA is made adaptive under different road conditions (slope angle and wind direction and speed). The vehicle was tested using the adaptive cruise control look-ahead energy management system, the results compared with the vehicle running the same test but without the adaptive cruise control look-ahead energy management system. The evaluation outcome indicates that the vehicle speed was efficiently controlled through the look-ahead methodology based upon the driving cycle, and that the average fuel consumption was reduced by 3%.

Intelligent energy management for plug-in hybrid electric vehicles : the role of ITS infrastructure in vehicle electrification

The desire to reduce carbon emissions due to transportation sources has led over the past decade to the development of new propulsion technologies, focused on vehicle electrification (including hybrid, plug-in hybrid and battery electric vehicles). These propulsion technologies, along with advances in telecommunication and computing power, have the potential of making passenger and commercial vehicles more energy efficient and environment friendly. In particular, energy management algorithms are an integral part of plug-in vehicles and are very important for achieving the performance benefits. The optimal performance of energy management algorithms depends strongly on the ability to forecast energy demand from the vehicle. Information available about environment (temperature, humidity, wind, road grade, etc.) and traffic (traffic density, traffic lights, etc.), is very important in operating a vehicle at optimal efficiency. This article outlines some current technologies that can help achieving this optimum efficiency goal. In addition to information available from telematic and geographical information systems, knowledge of projected vehicle charging demand on the power grid is necessary to build an intelligent energy management controller for future plug-in hybrid and electric vehicles. The impact of charging millions of vehicles from the power grid could be significant, in the form of increased loading of power plants, transmission and distribution lines, emissions and economics (information are given and discussed for the US case). Therefore, this effect should be considered in an intelligent way by controlling/scheduling the charging through a communication based distributed control.

Stochastic models of road geometry and wind condition for vehicle energy management and control

Modeling and simulation is commonly used to improve vehicle performance, to optimize vehicle system design, and to reduce vehicle development time. Vehicle performances can be affected by environmental conditions and driver behavior factors, which are often uncertain and immeasurable. To incorporate the role of environmental conditions in the modeling and simulation of vehicle systems, both real and artificial data are used. Often, real data are unavailable or inadequate for extensive investigations. Hence, it is important to be able to construct artificial environmental data whose characteristics resemble those of the real data for modeling and simulation purposes. However, to produce credible vehicle simulation results, the simulated environment must be realistic and validated using accepted practices. This paper proposes a stochastic model that is capable of creating artificial environmental factors such as road geometry and wind conditions. In addition, road geometric design principles are employed to modify the created road data, making it consistent with the real-road geometry. Two sets of real-road geometry and wind condition data are employed to propose probability models. To justify the distribution goodness of fit, Pearson's chi-square and correlation statistics have been used. Finally, the stochastic models of road geometry and wind conditions (SMRWs) are developed to produce realistic road and wind data. SMRW can be used to predict vehicle performance, energy management, and control strategies over multiple driving cycles and to assist in developing fuel-efficient vehicles.

Intelligent control and look-ahead energy management of hybrid electric vehicles

A review of the state of knowledge in the field of control and energy management in HEVs is carried out. The key innovation of the project is the development of a model of a PHEV using the real road data with an intelligent look-ahead online controller. Another novelty of this work is the method of route planning. It combines the information of vehicle sensors such as accelerometer and speedometer with the data of a GPS to create a road grade map for use within the look-ahead energy management strategy in the vehicle. For the PHEV, an adaptive cruise controller is modelled and an optimisation method is applied to obtain the best speed profile during a trajectory. Finally, the nonlinear model of the vehicle is applied with the sliding mode controller. The effect of using this controller is compared with the universal cruise controller. The stability of the system is studied and proved.