Online multiple classifier boosting for object tracking

This paper presents a new online multi-classifier boosting algorithm for learning object appearance models. In many cases the appearance model is multi-modal, which we capture by training and updating multiple strong classifiers. The proposed algorithm jointly learns the classifiers and a soft partitioning of the input space, defining an area of expertise for each classifier. We show how this formulation improves the specificity of the strong classifiers, allowing simultaneous location and pose estimation in a tracking task. The proposed online scheme iteratively adapts the classifiers during tracking. Experiments show that the algorithm successfully learns multi-modal appearance models during a short initial training phase, subsequently updating them for tracking an object under rapid appearance changes. © 2010 IEEE.

3D multi-car tracking based on monocular video

We propose a system that can reliably track multiple cars in congested traffic environments. Our system's key basis is the implementation of a sequential Monte Carlo algorithm, which introduces robustness against problems arising due to the proximity between vehicles. By directly modelling occlusions and collisions between cars we obtain promising results on an urban traffic dataset. Extensions to this initial framework are also suggested. © 2010 IEEE.

Multiple object tracking using evolutionary MCMC-based particle algorithms

Algorithms are presented for detection and tracking of multiple clusters of co-ordinated targets. Based on a Markov chain Monte Carlo sampling mechanization, the new algorithms maintain a discrete approximation of the filtering density of the clusters' state. The filters' tracking efficiency is enhanced by incorporating various sampling improvement strategies into the basic Metropolis-Hastings scheme. Thus, an evolutionary stage consisting of two primary steps is introduced: 1) producing a population of different chain realizations, and 2) exchanging genetic material between samples in this population. The performance of the resulting evolutionary filtering algorithms is demonstrated in two different settings. In the first, both group and target properties are estimated whereas in the second, which consists of a very large number of targets, only the clustering structure is maintained. © 2009 IFAC.

Stick held drag net for shore line fishes of reservoirs

Observations on the use of stick held drag nets for the removal of shore line fish, which adversely affect the growth of commercially important species in reservoirs, are presented.

Modified water spray chumming system for pole and line fishing of tuna

A water spray chumming system consisting of a 65 x 50 mm centrifugal pump driven by the propulsion engine through a PTO clutch and 'V' pulley power transmission system has been developed for the pole and line fishing of tuna. Water is sprayed through pipe loop system fitted on the edge of the fishing platform of the boat through small holes. The distance of the spray length can be adjusted by controlling the flow of the pump discharge water through a wheel valve.

Enhanced supply chain tracking based on the EPC network: A Bayesian approach

Supply chain tracking information is one of the main levers for achieving operational efficiency. RFID technology and the EPC Network can deliver serial-level product information that was never before available. However, these technologies still fail to meet the managers' visibility requirements in full, since they provide information about product location at specific time instances only. This paper proposes a model that uses the data provided by the EPC Network to deliver enhanced tracking information to the final user. Following a Bayesian approach, the model produces realistic ongoing estimates about the current and future location of products across a supply network, taking into account the characteristics of the product behavior and the configuration of the data collection points. These estimates can then be used to optimize operational decisions that depend on product availability at different locations. The enhancement of tracking information quality is highlighted through an example. © 2009 IFAC.

Shark long line gear of India

Sharks are mainly harvested with long lines which is less expensive compared to other methods of fishing. Though this is a common gear operated along the coast, the gear in every region has its own peculiarities in construction and rigging. This communication furnishes detailed description of the gear operated in different centres. Suggestions are also offered to improve the gear and methods for enhancing production.

Socio-economic and marketing aspects of Laila and Bottom Long Line fisheries in the Kalpitiya peninsula of Sri Lanka

Surrounding Net Fishery (laila) and Bottom Long Line Fishery which operate in the coastal waters of Kalpitiya Peninsula, compete for the same fish resources, resulting in a fishery dispute between the respective fishermen. Both fisheries target demersal as well as mid pelagic fishes, such as travellys (parava), mullets (galmalu) and barracudas (ulava). As the dispute had an adverse impact on the social harmony in the fishing community of the area, a socio-economic survey was conducted to study the underlying factors and to suggest policy measures to resolve the issue. The laila fishermen were resident fishermen in the Kalpitiya Peninsula while bottom long line fishermen were migratory fishermen from Negombo and Chilaw areas in the west coast of Sri Lanka. The Kalpitiya peninsula is located in the North West coast, some 50 km away from the west coast. Although the educational level and literacy rate of the laila community was below that of the bottom long line community, the laila community was economically better off. The net economic returns from laila fishery were superior to that from bottom long line fishery. The boat owner's and crew's share per operation of laila fishery were Rs.3,736 and Rs.947 respectively. The same figures for bottom long line fishery were Rs.588 and Rs.327 respectively. The resource rent from laila fishery was Rs.5,860, however, and much higher than that for bottom long line fishery (Rs.275), showing that the laila fishery exploits the targeted fish resource at a much higher rate compared to bottom long line fishery. This situation badly affects the equitable distribution of resources between the two fishing communities and results in unequal economic gains. Based on the findings of this study, certain input/output controls are proposed to address this problem, among which is the need to increase license fee for laila fishery units to offset the higher exploitation rate of fish resources.