Traditional forest-fire recognition based on the characteristics of smoke, temperature and light fails to accurately detect and respond to early fires. By analyzing the characteristics of flame, the methods based on a...Traditional forest-fire recognition based on the characteristics of smoke, temperature and light fails to accurately detect and respond to early fires. By analyzing the characteristics of flame, the methods based on aerial image recognition have been widely used, such as RGB-based and HIS-based methods. However, these methods are susceptible to background factors causing interference and false detection. To alleviate these problems, we investigate two subspace clustering methods based on sparse and collaborative representation, respectively, to detect and locate forest fires. Firstly, subspace clustering segments flame from the whole image. Afterwards, sparse or collaborative representation is employed to represent most of the flame information in a dictionary with l1-regularization or l2-regularization term, which results in fewer reconstruction errors. Experimental results show that the proposed SSC and CSC substantially outperform the state-of-the art methods.展开更多
The influences of finite-size effects on the self-organized criticality (SOC) of the traditional forest-fire model are investigated by means of a new method. The forest size is originally set to a value much greater t...The influences of finite-size effects on the self-organized criticality (SOC) of the traditional forest-fire model are investigated by means of a new method. The forest size is originally set to a value much greater than the correla-tion length of the forest. Finite-size effects are then studied by equally dividing the forest into more and more separate subsystems on condition that the forest size, igniting prob-ability and planting probability are invariant. A new phe-nomenon, i.e. the finite-size effects with one-side frequency peak, is observed. The boundary between two neighboring subsystems can be regarded as a firebreak. The concept of ’separation ability’ is introduced to represent the probability for the firebreak to block off the fire successfully. Restrain-ing effects of separation ability on finite-size effects are ana-lyzed. Finite-size effects and separation ability, as well as their relations are found to have practical importance to the actual forest-fire protection.展开更多
文摘Traditional forest-fire recognition based on the characteristics of smoke, temperature and light fails to accurately detect and respond to early fires. By analyzing the characteristics of flame, the methods based on aerial image recognition have been widely used, such as RGB-based and HIS-based methods. However, these methods are susceptible to background factors causing interference and false detection. To alleviate these problems, we investigate two subspace clustering methods based on sparse and collaborative representation, respectively, to detect and locate forest fires. Firstly, subspace clustering segments flame from the whole image. Afterwards, sparse or collaborative representation is employed to represent most of the flame information in a dictionary with l1-regularization or l2-regularization term, which results in fewer reconstruction errors. Experimental results show that the proposed SSC and CSC substantially outperform the state-of-the art methods.
基金This work was supported by the National Basic Research "973" Project in China the National Natural Science Foundation in China (Grant Nos. 59876039, 59936140 and 39970621).
文摘The influences of finite-size effects on the self-organized criticality (SOC) of the traditional forest-fire model are investigated by means of a new method. The forest size is originally set to a value much greater than the correla-tion length of the forest. Finite-size effects are then studied by equally dividing the forest into more and more separate subsystems on condition that the forest size, igniting prob-ability and planting probability are invariant. A new phe-nomenon, i.e. the finite-size effects with one-side frequency peak, is observed. The boundary between two neighboring subsystems can be regarded as a firebreak. The concept of ’separation ability’ is introduced to represent the probability for the firebreak to block off the fire successfully. Restrain-ing effects of separation ability on finite-size effects are ana-lyzed. Finite-size effects and separation ability, as well as their relations are found to have practical importance to the actual forest-fire protection.
