LiDAR-assisted Large-scale Privacy Protection in Street-view Cycloramas
This work addresses privacy protection for street-view image providers by providing a more efficient solution, though it is incremental as it builds on existing detection and blurring techniques.
The paper tackles the problem of high processing costs for privacy protection in high-resolution street-view images by proposing a LiDAR-assisted system that reduces detection search space, achieving cost-effectiveness at 2.5x higher resolution and offering a faster, higher-performance alternative to existing methods.
Recently, privacy has a growing importance in several domains, especially in street-view images. The conventional way to achieve this is to automatically detect and blur sensitive information from these images. However, the processing cost of blurring increases with the ever-growing resolution of images. We propose a system that is cost-effective even after increasing the resolution by a factor of 2.5. The new system utilizes depth data obtained from LiDAR to significantly reduce the search space for detection, thereby reducing the processing cost. Besides this, we test several detectors after reducing the detection space and provide an alternative solution based on state-of-the-art deep learning detectors to the existing HoG-SVM-Deep system that is faster and has a higher performance.