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

In this paper, we address the issue of designing a smoke detector robust to illumination variations. Our contribution consists in resorting to color invariants as salient smoke features. More precisely, the proposed detector employs consecutively of an illumination invariant color representation, a photometric gain based background subtraction, a chrominance detection and a smoke identification based on two invariant color descriptors.

Additional depth information from RGBD images is one of characteristics different from conventional 2D images. Saliency detection aims to detect the attractive objects to human viewers in an image. Generally, saliency cues from different features are measured and fused into a single saliency using a linear or experiential fusion formula. we introduce a multi-stage depth-aware saliency model to fuse multiple saliency maps in a discriminative method.

The movement of tongue plays an important role in pronunciation. Visualizing the movement of tongue can improve speech intelligibility and also helps learning a second language. However, hardly any research has been investigated for this topic. In this paper, a framework to synthesize continuous ultrasound tongue movement video from speech is presented. Two different mapping methods are introduced as the most important parts of the framework. The objective evaluation and subjective opinions show that the Gaussian

By exploiting the geometry information, the estimation performance (efficiency, accuracy and robustness) can be improved, and the conventional searching procedure can also be avoided. The concept of the methods can be used in the parameters estimation field, especially .

Visual tracking in unconstrained environments often involves following an object that exhibits a number of appearance changes from factors such as scale change, rotation, and illumination. Effective tracking requires adapting a tracker to the object’s changing appearance over time. When a target becomes occluded by other objects in the scene, a naive tracker may end up learning the appearance of the occluding object. Our work introduces a method of detecting occlusion by considering the color profile of the target to prevent inappropriate tracker updates while the target is occluded.