No abstract

Ship detection in optical remote sensing images 1 has potential applications in national maritime security, fishing, 2 and defense. Many detectors, including computer vision and 3 geoscience-based methods, have been proposed in the past decade. 4 Recently, deep learning-based algorithms have also achieved 5 great success in the field of ship detection. However, most of 6 the existing detectors face difficulties in complex environments, 7 small ship detection, and fine-grained ship classification. One 8 reason is that existing datasets have shortcomings in terms of 9 the inadequate number of images, few ship categories, image diversity, and insufficient variations. This paper publishes a 11 public ship detection dataset, namely ShipRSImageNet, which 12 contributes an accurately labeled dataset in different scenes with 13 variant categories and image sources. The proposed ShipRSIm-ageNet contains over 3,435 images with 17,573 ship instances in 15 50 categories, elaborately annotated with both horizontal and 16 orientated bounding boxes by experts. From our knowledge, up 17 to now, the proposed ShipRSImageNet is the largest remote 18 sensing dataset for ship detection. Moreover, several state-of-19 the-art detection algorithms are evaluated on our proposed 20 ShipRSImageNet dataset to give a benchmark for deep learning-21 based ship detection methods, which is valuable for assessing 22 algorithm improvement. The dataset has been released at https:

Video-based multiple human tracking often involves several challenges, including target number variation, object occlusions, and noise corruption in sensor measurements. In this paper, we propose a novel method to address these challenges based on probability hypothesis density (PHD) filtering with a Markov chain Monte Carlo (MCMC) implementation. More specifically, a novel social force model (SFM) for describing the interaction between the targets is used to calculate the likelihood within the MCMC resampling step in the prediction step of the PHD filter, and a one class support vector machine (OCSVM) is then used in the update step to mitigate the noise in the measurements, where the SVM is trained with features from both color and oriented gradient histograms. The proposed method is evaluated and compared with state-of-the-art techniques using sequences from the CAVIAR, TUD, and PETS2009 datasets based on the mean Euclidean tracking error on each frame, the optimal subpattern assignment metric, and the multiple object tracking precision metric. The results show improved performance of the proposed method over the baseline algorithms, including the traditional particle PHD filtering method, the traditional SFM-based particle filtering method, multi-Bernoulli filtering, and an online-learningbased tracking method. Index Terms-Multiple human tracking, Markov chain Monte Carlo (MCMC) resampling, one class support vector machine (OCSVM), probable hypothesis density (PHD) filter, social force model. I. INTRODUCTIONV IDEO based multiple human tracking plays an important role in many applications such as surveillance, guidance, and homeland security, especially in enclosed environments such as an airport, campus or shopping mall. Tracking multiple human targets in the above situations presents several challenges including varying number of targets, object occlusion, and the adverse effect of environmental noise within measurements [1],

We propose a novel computer vision based fall detection system using deep learning methods to analyse the postures in a smart home environment for detecting fall activities. Firstly, background subtraction is employed to extract the foreground human body. Then the binary human body images form the input to the classifier. Two deep learning approaches based on a Boltzmann machine and deep belief network are compared with a support vector machine approach. The final decision on the occurrence of a fall is made on the basis of combining the classifier output with certain contextual rules. Evaluations are performed on recordings from a real home care environment, in which 15 people create 2904 postures.

We present a novel unsupervised fall detection system that employs the collected acoustic signals (footstep sound signals) from an elderly person’s normal activities to construct a data description model to distinguish falls from non-falls. The measured acoustic signals are initially processed with a source separation (SS) technique to remove\ud the possible interferences from other background sound sources. Mel-frequency cepstral coefficient (MFCC) features are next extracted from the processed signals and used to construct a data description model based on a one class support vector machine (OCSVM) method, which is finally applied to distinguish fall from non-fall sounds. Experiments on a recorded dataset confirm that our proposed fall detection system can achieve better performance, especially with high level of interference from other sound sources, as compared with existing single microphone based methods