Using machine vision classification to control access of animals to water

摘要: Invasive vertebrate pests together with overabundant native species cause significant economic and environmental damage in the Australian rangelands. Access to artificial watering points, created for pastoral industry, has been a major factor spread survival of these pests. Existing methods controlling points are mechanical cannot discriminate between target species. This paper describes an intelligent system based on machine vision technology. Initial test results clearly demonstrate proof concept this application. These initial experiments were carried out as part 3-year project using software manage all large vertebrates Concurrent work is testing use automated gates innovative laneway enclosure design. The will have application any habitat throughout world where resource limited can be enclosed management livestock or wildlife.