Power-line-strike accident is a major safety threat for low-flying aircrafts such as helicopters, thus an automatic warning system to power lines is highly desirable. In this paper we propose an algorithm for detecting power lines from radar videos from an active millimeter-wave sensor. Hough Transform is employed to detect candidate lines. The major challenge is that the radar videos are very noisy due to ground return. The noise points could fall on the same line which results in signal peaks after Hough Transform similar to the actual cable lines. To differentiate the cable lines from the noise lines, we train a Support Vector Machine to perform the classification. We exploit the Bragg pattern, which is due to the diffraction of electromagnetic wave on the periodic surface of power lines. We propose a set of features to represent the Bragg pattern for the classifier. We also propose a slice-processing algorithm which supports parallel processing, and improves the detection of cables in a cluttered background. Lastly, an adaptive algorithm is proposed to integrate the detection results from individual frames into a reliable video detection decision, in which temporal correlation of the cable pattern across frames is used to make the detection more robust. Extensive experiments with real-world data validated the effectiveness of our cable detection algorithm.

No abstract

In this paper, we propose a tracking algorithm to detect power lines from millimeter-wave radar video. We propose a general framework of cascaded particle filters which can naturally capture the temporal correlation of the power line objects, and the power-line-specific feature is embedded into the conditional likelihood measurement process of the particle filter. Because of the fusion of multiple information sources, power line detection is more effective than the previous approach. Both the accuracy and the recall of power line detection are improved from around 68 to over 92.

We propose a new error concealment method based on hallucination for Scalable Video Coding with spatial scalability. In this method, parts of the frames which lose the enhancement layer are up-sampled from base layer and "hallucinated" as concealment frames. The database for hallucination is generated from the high-resolution and low-resolution frame-pairs near the lost frames in the video sequence. The effectiveness of hallucination here lies in the similarity between the nearby frames in the video sequence. Experiments show that the proposed method has superior results over the state-of-the-art error concealment method for spatially Scalable Video Coding.978-1-4244-3828-0/09/$25.00 ©2009 IEEE