The autonomous parking of vehicles requires the ability to accurately locate an available parking slot in the vicinity of a vehicle. Since parking slots have a variety of shapes and colors, may be occluded by obstacles, or look different due to surroundings such as lighting, accurately locating them can be a challenging task. In this paper, we propose a context-based parking slot detection method inspired by the process of a human driver finding a parking slot. Our method consists of two deep network modules: a parking context recognizer and parking slot detector. The parking context recognizer identifies the parking environment (type, angle, and availability of a parking slot), whereas the parking slot detector locates the exact position of a parking slot by multiple type-based fine-tuned detectors with rotated anchor boxes and a rotated non-maximal suppression. In addition, we release a realistic parking slot dataset, which comprises 22817 images of parking slots having various attributes and external conditions. We also propose a new evaluation metric for parking slot detection, reflecting whether a vehicle can be parked within the detected parking slot. Through comparison and ablation study in experiments, we demonstrate that our method outperformed the previous deep-learning-based methods, along with having a short operation time.

No abstract

This paper presents a blind digital video watermarking watermark pattern is obtained from the watermarked and scheme, which is especially robust to camcorder recording attacks attacked frames, hence it is a blind scheme. The generated and also to a variety of common video processing and geometric pattern is then correlated to the video frames to extract the distortions. Using the fact that nearby frames of a video sequence information embedded by temporal modulation.are quite similar, the method embeds the watermark by temporal modulation of the frames. The watermark pattern used in modulation is generated based on the pixel-value histogram, which II. WATERMARK EMBEDDING makes extraction free from geometric synchronization. To make it imperceptible, the watermark is adjusted according roughly to the A. Temporal Modulation Human Visual System. The experimental results demonstrate the robustness of the proposed method to camcorder recording attacks Our scheme uses temporal modulation to embed the also involving geometric distortions and other video processing watermark information. A group of 5 consecutive frames, attacks such as MPEG and other compressions.called watermarking group of pictures (WGP), is used for temporal modulation. To embed one bit of information, the Keywords -videowt ar camc reording, frames in a WGP is modulated by either adding or watermprkal m tin subtracting a watermark pattern to and from the frames, respectively, according to the bit. In particular, to embed the