On-board Detection System Research Articles

SEADETECT: developing an automated detection system to reduce whale-vessel collision risk

With the continuous intensification of marine traffic worldwide, whale-vessel collisions at sea (or “ship strikes”) have become one of the primary causes of mortality for cetaceans and a widely recognised cause of concern for human safety and economic losses. The Mediterranean Sea is a global hotspot for whale-vessel collisions, with one of the highest rates involving large cetaceans, especially the endangered fin whales (Balaenoptera physalus) and sperm whales (Physeter macrocephalus). Evidence indicates that both species are experiencing higher chances of a fatal collision than what predictions have estimated so far, with ship strikes being the main human-induced threat in the area. Regional and international organisations have stressed the need to address the issue by investigating the projected impacts of ship strikes on whale populations and by identifying possible mitigation measures to reduce chances of collision. Amongst the most popular and feasible options, there is the improvement of animal detection during navigation. Here, we present SEADETECT, a LIFE project that aims at developing an automated detection system to reduce vessel collision risk with marine mammals and unidentified floating objects (UFOs), combining state-of-the-art and novel technologies with existing approaches in the study of large whale ecology. This detection system consists of three elements; an automated onboard detection system composed of several sensors, a real-time passive acoustic monitoring (PAM) network at sea and a real-time detection-sharing and alert system (REPCET®). In this paper, we propose the development of a mitigation measure framework tailored for the issue of collision with fin and sperm whales in the north-western Mediterranean Sea, but that has the transferability features necessary for its application in other high-risk areas for ship strikes worldwide.

Effectiveness of surface-based detection methods for vessel strike mitigation of North Atlantic right whales

Increasing commercial and recreational use of the world’s oceans has led to growing concerns about vessel and marine mammal encounters. For endangered species such as the North Atlantic right whale Eubalaena glacialis, reducing the number of vessel strikes is key to improving their protection. In this study, we developed an agent-based model to assess the efficacy of thermal imaging systems as a surface-based whale detection method for vessel strike mitigation. We found that the detection range of such systems is the determining factor for their efficacy and needs to be chosen according to vessel characteristics, such as speed and maneuverability. Furthermore, we found that combining large-scale (e.g. protected zones) and small-scale (e.g. on-board detection systems) mitigation strategies increases protection. Finally, technological improvements are needed to achieve reliable detection ranges beyond what is currently possible so that fast and poorly maneuverable vessels such as ultra-large container ships could benefit from on-board detection systems.

Three-Dimensional Autonomous Obstacle Avoidance Algorithm for UAV Based on Circular Arc Trajectory

This paper proposes an innovative and efficient three-dimensional (3D) autonomous obstacle algorithm for unmanned aerial vehicles (UAVs) which works by generating circular arc trajectories to avoid obstacles. Firstly, information on irregular obstacles is obtained by an onboard detection system; this information is then transformed into standard convex bodies, which are used to generate circular arc avoidance trajectories, and the obstacle avoidance problem is turned into a trajectory tracking strategy. Then, on the basis of the geometric relationship between a UAV and obstacle modeling, the working mechanism of the avoidance algorithm is developed. The rules of obstacle detection, avoidance direction, and the criterion of avoidance success are defined for different obstacle types. Finally, numerical simulations of different obstacle scenarios show that the proposed algorithm can avoid static and dynamic obstacles effectively and can implement obstacle avoidance missions for UAVs well.

A Real-Time Fault Early Warning Method for a High-Speed EMU Axle Box Bearing.

An axle box bearing is one of the most important components of high-speed EMUs (electric multiple units), which runs at a very fast speed, suffers a heavy load, and operates under various complex working conditions. Once a bearing fault occurs, it not only has an enormous impact on the railway system, but also poses a threat to personal safety. Therefore, there is significant value in studying a real-time fault early warning of a high-speed EMU axle box bearing. However, to our best knowledge, there are three obvious defects in the existing fault early warning methods used for high-speed EMU axle box bearings: (1) these methods based on vibration are extremely mature, but there are no vibration sensors installed in high-speed EMU axle box because it will greatly increase the manufacturing cost; (2) a TADS (trackside acoustic device system) can effectively detect early failures, but only a portion of railways are equipped with such a facility; and (3) an EMU-ODS (electric multiple unit onboard detection system) has reported numerous untimely warnings, along with warnings of frequent occurrence being missed. Whereupon, a method is proposed to realize the fault early warning of an axle box bearing without installing a vibration sensor on the high-speed EMU in service, namely a MLSTM-iForest (multilayer long short-term memory–isolation forest). First, the time-series data of the temperature-related variables of the axle box bearing is used as the input of MLSTM to predict the axle box bearing temperature in the future. Then, the deviation index of the predicted axle box bearing temperature is calculated. Finally, the deviation index is input into an iForest algorithm for unsupervised classification to realize the fault early warning of an axle box bearing. Experimental results on high-speed EMU operation data sets demonstrated the availability and feasibility of the presented method toward achieving early fault warnings of a high-speed EMU axle box bearing.

A MODEL AND TRAINING ALGORITHM OF SMALL-SIZED OBJECT DETECTION SYSTEM FOR A COMPACT AERIAL DRONE

Context. Lightweight model and effective training algorithm of on-board object detection system for a compact drone are developed. The object of research is the process of small object detection on aerial images under computational resource constraint and uncertainty caused by small amount of labeled training data. The subject of the research are the model and training algorithm for detecting small objects on aerial imagery. Objective. Goal of the research is developing efficient model and training algorithm of object detection system for a compact aerial drone under conditions of restricted computing resources and the limited volume of the labeled training set. Methods. The four-stage training algorithm of the object detector is proposed. At the first stage, selecting the type of deep convolutional neural network and the number of low-level layers that is pre-trained on the ImageNet dataset for reusing takes place. The second stage involves unsupervised training of high-level convolutional sparse coding layers using modification of growing neural gas to automatically determine the required number of neurons and provide optimal distributions of the neurons over the data. Its application makes it possible to utilize the unlabeled training datasets for the adaptation of the high-level feature description to the domain application area. At the third stage, there are reduction of output feture map using principan component analysis and building of decision rules. In this case, output feature map is formed by concatenation of feature maps from different level of deep network using upscaling upper maps to uniform shape for each channel. This approach provides more contextual information for efficient recognition of small objects on aerial images. In order to build classifier of output feature map pixels is proposed to use boosted information-extreme learning. Besides that, the extreme learning machine is used to build of regression model for predict bounding box of detected object. Last stage involves fine-tuning of high-level layers of deep network using simulated annealing metaheuristic algorithm in order to approximating the global optimum of complex criterion of training efficiency of detection model. Results. The results obtained on open datasets testify to the suitability of the model and training algorithm for practical usage. The proposed training algorithm utilize 500 unlabeled and 200 labeled training samples to provide 96% correctly detection of objects on the images of the test dataset. Conclusions. Scientific novelty of the paper is a new model and training algorithm for object detection, which enable to achieve high confidence of recognition of small objects on aerial images under computational resource constraint and limited volume of the labeled training set. Practical significance of the paper results consists in the developed model and training algorithm made it possible to reduce requirements for size of labeled training set and computation resources of on-board detection system of aerial drone in training and inference modes.

Technological Response Options after the VW Diesel Scandal: Implications for Engine CO2 Emissions

In the VW diesel scandal, automakers were found to be cheating with emission data, by e.g., tampering with on-board detection systems. We have calculated changes in the energy use and emissions of carbon dioxide equivalents that would arise through several options open to automakers, to ensure that the emission of nitrogen oxides is kept within the standards. Several studies show how manufacturers have also significantly underreported vehicles’ actual fuel consumption. We explain our derivation of new factors for energy consumption and greenhouse gas emissions from diesel- and gasoline-powered passenger cars, as well as their electric hybrid varieties. The results of the analysis show that energy consumption and emissions of carbon dioxide equivalents will increase in the range of 18–21% for passenger cars with diesel and hybrid diesel engines, while for cars with gasoline and hybrid gasoline, the addition is 9–10%. The analysis highlights an environmental dilemma of current car technology, but also the path-dependent ways of thinking that have been prevalent within the automotive sector. From a sociotechnical sustainability transitions perspective, Dieselgate can be viewed as a case of “regime resistance”, whereby incumbent actors seek to maintain the status quo.

Subunit and Catalytic Component Stoichiometries of an in Vitro Reconstituted Human Pyruvate Dehydrogenase Complex

The human pyruvate dehydrogenase complex (PDC) is a 9.5-megadalton catalytic machine that employs three catalytic components, i.e. pyruvate dehydrogenase (E1p), dihydrolipoyl transacetylase (E2p), and dihydrolipoamide dehydrogenase (E3), to carry out the oxidative decarboxylation of pyruvate. The human PDC is organized around a 60-meric dodecahedral core comprising the C-terminal domains of E2p and a noncatalytic component, E3-binding protein (E3BP), which specifically tethers E3 dimers to the PDC. A central issue concerning the PDC structure is the subunit stoichiometry of the E2p/E3BP core; recent studies have suggested that the core is composed of 48 copies of E2p and 12 copies of E3BP. Here, using an in vitro reconstituted PDC, we provide densitometry, isothermal titration calorimetry, and analytical ultracentrifugation evidence that there are 40 copies of E2p and 20 copies of E3BP in the E2p/E3BP core. Reconstitution with saturating concentrations of E1p and E3 demonstrated 40 copies of E1p heterotetramers and 20 copies of E3 dimers associated with the E2p/E3BP core. To corroborate the 40/20 model of this core, the stoichiometries of E3 and E1p binding to their respective binding domains were reexamined. In these binding studies, the stoichiometries were found to be 1:1, supporting the 40/20 model of the core. The overall maximal stoichiometry of this in vitro assembled PDC for E2p:E3BP:E1p:E3 is 40:20:40:20. These findings contrast a previous report that implicated that two E3-binding domains of E3BP bind simultaneously to a single E3 dimer (Smolle, M., Prior, A. E., Brown, A. E., Cooper, A., Byron, O., and Lindsay, J. G. (2006) J. Biol. Chem. 281, 19772-19780).

The feasibility of detecting phone-use related driver distraction

Apart from the driving behavioural change that can be the direct consequence of operating a car phone, phone-use related behaviour may also be a threat to traffic safety. Making notes or looking up telephone numbers while driving are examples of such behaviour. In a driving simulator experiment, 20 drivers drove in two conditions under normal driving conditions and while being because of telephone engagement. In the distracted condition they had to handle a mobile phone while their attention was drawn off the road for up to several seconds by a telephone number search task. Results showed both a deterioration in driver performance on different vehicle parameters including behavioural (speed) compensation as a result of the demanding telephone task. In an effort to develop an on-board detection system for this type of driver inattention, the data were used to serve as input for a real time diagnosis system based on Statistics, Artificial Neural Networks (ANNs) and Fuzzy Logic (FL). System performance in recognising normal and deteriorated driving behaviour was 89%. On-line detection of driver distraction is considered feasible in the near future.