No abstract

a b s t r a c tThe Shortest Common Supersequence Problem asks to obtain a shortest string that is a supersequence of every member of a given set of strings. It has applications, among others, in data compression and oligonucleotide microarray production. The problem is NP-hard, and the existing exact solutions are impractical for large instances. In this paper, a new beam search algorithm is proposed for the problem, which employs a probabilistic heuristic and uses the dominance property to further prune the search space. The proposed algorithm is compared with three recent algorithms proposed for the problem on both random and biological sequences, outperforming them all by quickly providing solutions of higher average quality in all the experimental cases. The Java source and binary files of the proposed IBS_SCS algorithm and our implementation of the DR algorithm and all the random and real datasets used in this paper are freely available upon request.

Background subtraction is a fundamental task in computer vision with numerous real-world applications, ranging from object tracking to video surveillance. However, dynamic backgrounds can pose a significant challenge in this problem. While various methods have been proposed for background subtraction, supervised deep learning-based techniques are currently considered state-of-the-art. However, these methods require pixelwise ground-truth labeling, which can be time-consuming and expensive. In this work, we propose a weakly supervised framework that can perform background subtraction without requiring perpixel ground-truth labels. Our framework is trained on a moving object-free sequence of images and comprises two networks. The first network is an autoencoder that generates static background images and prepares dynamic background images for training the second network. The dynamic background images are obtained by thresholding the background-subtracted images. The second network is a U-Net that uses the same moving object-free video for training and the dynamic background images as pixel-wise ground-truth labels. During the test phase, the input images are processed by the autoencoder and U-Net, which generate static and dynamic background images, respectively. The dynamic background image helps remove dynamic motion from the background subtracted image, enabling us to obtain a foreground image that is free of dynamic artifacts. To demonstrate the effectiveness of our method, we conducted experiments on selected categories of the CDnet 2014 dataset and the I2R dataset. Our method outperformed all top-ranked unsupervised methods. It also surpassed one of the two existing weakly supervised methods, while achieving comparable results to the other method but with a shorter running time. Our proposed method is online, realtime, efficient, and requires minimal frame-level annotation, making it suitable for a wide range of real-world applications.

No abstract

Moving object detection (MOD) is a significant problem in computer vision that has many real world applications. Different categories of methods have been proposed to solve MOD. One of the challenges is to separate moving objects from illumination changes and shadows that are present in most real world videos. State-of-the-art methods that can handle illumination changes and shadows work in a batch mode; thus, these methods are not suitable for long video sequences or real-time applications. In this paper, we propose an extension of a state-of-the-art batch MOD method (ILISD) [23] to an online/incremental MOD using unsupervised and generative neural networks, which use illumination invariant image representations. For each image in a sequence, we use a low-dimensional representation of a background image by a neural network and then based on the illumination invariant representation, decompose the foreground image into: illumination change and moving objects. Optimization is performed by stochastic gradient descent in an end-to-end and unsupervised fashion. Our algorithm can work in both batch and online modes. In the batch mode, like other batch methods, optimizer uses all the images. In online mode, images can be incrementally fed into the optimizer. Based on our experimental evaluation on benchmark image sequences, both the online and the batch modes of our algorithm achieve state-of-the-art accuracy on most data sets.