Intelligent animal detection system using sparse multi discriminative-neural network (SMD-NN) to mitigate animal-vehicle
- PDF / 11,806,219 Bytes
- 16 Pages / 595.276 x 790.866 pts Page_size
- 54 Downloads / 226 Views
RESEARCH ARTICLE
Intelligent animal detection system using sparse multi discriminative-neural network (SMD-NN) to mitigate animal-vehicle collision S Divya Meena 1 & Agilandeeswari Loganathan 1 Received: 11 February 2020 / Accepted: 29 June 2020 # Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Animal-Vehicle Collision (AVC) is a predominant problem in both urban and rural roads and highways. Detecting animals on the road is challenging due to factors like the fast movement of both animals and vehicles, highly cluttered environmental settings, noisy images, and occluded animals. Deep learning has been widely used for animal applications. However, they require large training data; henceforth, the dimensionality increases, leading to a complex model. In this paper, we present an animal detection system for mitigating AVC. The proposed system integrates sparse representation and deep features optimized with FixResNeXt. The deep features extracted from candidate parts of the animals are represented in a sparse form using a feature-efficient learning algorithm called Sparse Network of Winnows (SNoW). The experimental results prove that the proposed system is invariant to the viewpoint, partial occlusion, and illumination. On the benchmark datasets, the proposed system has achieved an average accuracy of 98.5%. Keywords Animal-vehicle collision . Animal detection . Deep features . Sparse representation . Sparse Network of Winnows
Introduction Animal-vehicle collision (AVC) signifies the mounting issues in terms of conservation, safety to both animals and humans, as well as the financial apprehensions across India, specifically the Southern zone. Both animals and humans are crashing together on the roads, leading to loss of life. All these crashes are due to the rapid depletion of the forest, which is being used for the various human causes like urban sprawl, expanding the infrastructure for transportation, etc. Most instances of AVCs are by far reported in the rural settings. However, with the ongoing rapid destruction of the forest, sooner, both the urban and suburban landscapes will be occupied. According to a report (Bíl et al. 2019), by 2050, urban areas alone will be holding approximately 6.3 billion people. Such engorgement of cities will have a higher traffic rate with unprecedented road use, and this will have a higher number of accidents involving
Responsible editor: Philippe Garrigues * Agilandeeswari Loganathan [email protected] 1
School of Information and Technology, Vellore Institute of Technology, Vellore, India
AVC. However, only very few cities are equipped with facilities to mitigate AVC. According to Society for Prevention of Cruelty to Animals (SPCA) (Sharma and Shah, 2016), approximately 500 cattle were admitted in the past 3 years, and 90% of the cases were due AVC. Animal detection systems are mostly developed for real-time animal monitoring applications like human-animal conflict (Divya and Agilandeeswari 2019), animal-vehicle collision (Meena and Agilandeeswari 2020), ani
Data Loading...
