Sorry, you need to enable JavaScript to visit this website.

Scene text detection is a critical prerequisite for many fascinating applications for vision-based intelligent robots. Existing methods detect texts either using the local information only or casting it as a semantic segmentation problem. They tend to produce a large number of false alarms or cannot separate individual words accurately. In this work, we present an elegant segmentation-aided text detection solution that predicts the word-level bounding boxes using an end-to-end trainable deep convolutional neural network.

Assistive technologies such as wheelchairs, canes, and walkers have significantly improved the mobility, function, and quality of life for individuals with spinal cord injury (SCI). In this article, we propose a framework which combines machine learning algorithms with wearable sensors to capture and track mobility in individuals with SCI. Pilot testing in two individuals without SCI indicated that four to seven features obtained from sensors worn on the body or placed on the assistive technology could successfully detect mobility and mobility modes.

Scene text detection is a critical prerequisite for many fascinating applications for vision-based intelligent robots. Existing methods detect texts either using the local information only or casting it as a semantic segmentation problem. They tend to produce a large number of false alarms or cannot separate individual words accurately. In this work, we present an elegant segmentation-aided text detection solution that predicts the word-level bounding boxes using an end-to-end trainable deep convolutional neural network.

Introductory derivations are done before introducing the metric of Fisher’s LDA. Then, after introducing Fisher's LDA and its different forms, Fisher’s Metrics and their maximizations are given. The idea of traces in Fisher's LDA is explained. Weighted features method is used for feature selection. Various simple examples are provided to clarify the idea for the feature selection.

Background subtraction from the given image is a widely used method for moving object detection. However, this method is vulnerable to dynamic background in a moving camera video. In this paper, we propose a novel moving object detection approach using deep learning to achieve a robust performance even in a dynamic background. The proposed approach considers appearance features as well as motion features. To this end, we design a deep learning architecture composed of two networks: an appearance network and a motion network.

In this paper, we propose a novel coupled dictionary learning method, namely coupled analysis-synthesis dictionary learning, to improve the performance of person re-identification in the non-overlapping fields of different camera views. Most of the existing coupled dictionary learning methods train a coupled synthesis dictionary directly on the original feature spaces, which limits the representation ability of the dictionary.

We investigate video classification via a 3D deep convolutional neural network (CNN) that directly ingests compressed bitstream information. This idea is based on the observation that video macroblock (MB) motion vectors (that are very compact and directly available from the compressed bitstream) are inherently capturing local spatiotemporal changes in each video scene.