Open-set classification is a problem of handling 'unknown' classes that are not contained in the training dataset, whereas traditional classifiers assume that only known classes appear in the test environment. Existing open-set classifiers rely on deep networks trained in a supervised manner on known classes in the training set; this causes specialization of learned representations to known classes and makes it hard to distinguish unknowns from knowns. In contrast, we train networks for joint classification and reconstruction of input data. This enhances the learned representation so as to preserve information useful for separating unknowns from knowns, as well as to discriminate classes of knowns. Our novel Classification-Reconstruction learning for Open-Set Recognition (CROSR) utilizes latent representations for reconstruction and enables robust unknown detection without harming the known-class classification accuracy. Extensive experiments reveal that the proposed method outperforms existing deep open-set classifiers in multiple standard datasets and is robust to diverse outliers. The code is available in https://nae-lab.

For assistance with grazing cattle management, we propose a cattle detection and counting system based on Convolutional Neural Networks (CNNs) using aerial images taken by an Unmanned Aerial Vehicle (UAV). To improve detection performance, we take advantage of the fact that, with UAV images, the approximate size of the objects can be predicted when the UAV's height from the ground can be assumed to be roughly constant. We resize an image to be fed into the CNN to an optimum resolution determined by the object size and the down-sampling rate of the network, both in training and testing. To avoid repetition of counting in images that have large overlaps to adjacent ones and to obtain the accurate number of cattle in an entire area, we utilize a three-dimensional model reconstructed by the UAV images for merging the detection results of the same target. Experiments show that detection performance is greatly improved when using the optimum input resolution with an F-measure of 0.952, and counting results are close to the ground truths when the movement of cattle is approximately stationary compared to that of the UAV's.

Collisions of birds, especially endangered species, with wind turbines is a major environmental concern. Automatic bird monitoring can be of aid in resolving the issue, particularly in environmental risk assessments and real‐time collision avoidance. For automatic recognition of birds in images, a clean, detailed, and realistic dataset to learn features and classifiers is crucial for any machine‐learning‐based method. Here, we constructed a bird image dataset that is derived from the actual environment of a wind farm and that is useful for examining realistic challenges in bird recognition in practice. It consists of high‐resolution images covering a wide monitoring area around a turbine. The birds captured in these images are at relatively low resolution and are hierarchically labeled by experts for fine‐grained species classification. We conducted evaluations of state‐of‐the‐art image recognition methods by using this dataset. The evaluations revealed that a deep‐learning‐based method and a simpler traditional learning method were almost equally successful at detection, while the former captures more generalized features. The most promising results were provided by the deep‐learning‐based method in classification. The best methods in our experiments recorded a 0.98 true positive rate for bird detection at a false positive rate of 0.05 and a 0.85 true positive rate for species classification at a false positive rate of 0.1.

No abstract

Demand for automatic bird ecology investigation rises rapidly along with the widespread installation of wind energy plants to estimate their adverse environmental effect. While significant advance in general image recognition has been made by deep convolutional neural networks (CNNs), automatically recognizing birds at small scale together with large background regions is still an open problem in computer vision. To tackle object detection at various scales, we combine a deep detector with semantic segmentation methods; namely, we train a deep CNN detector, fully convolutional networks (FCNs), and the variant of FCNs, and integrate their results by the support vector machines to achieve high detection performance. Through experimental results on a bird image dataset, we show the effectiveness of the method for scale-aware object detection.