Surround-view fisheye cameras are commonly used for near-field sensing in automated driving scenarios, including urban driving and auto valet parking. Four fisheye cameras, one on each side, are sufficient to cover 360° around the vehicle capturing the entire near-field region. Based on surround view cameras, there has been much research on parking slot detection with main focus on the occupancy status in recent years, but little work on whether the free slot is compatible with the mission of the ego vehicle or not. For instance, some spots are handicap or electric vehicles accessible only. In this paper, we tackle parking spot classification based on the surround view camera system. We adapt the object detection neural network YOLOv4 with a novel polygon bounding box model that is well-suited for various shaped parking spaces, such as slanted parking slots. To the best of our knowledge, we present the first detailed study on parking spot detection and classification on fisheye cameras for auto valet parking scenarios. The results prove that our proposed classification approach is effective to distinguish between regular, electric vehicle, and handicap parking spots.
Automatic X-ray inspection of industrial parts usually uses reference-based methods, in which a set of model images or statistics extracted from the model image set are selected as the benchmark. Based on these methods, many systems are developed and are used extensively for anomaly detection. However, the performance of these systems relies heavily on the model image set. Thus, the selection of the model images is very important. This paper presents an approach for automatically selecting a set of model images to be used in a reference-based assisted defect recognition (ADR) system for anomaly detection of turbine blades of jet engines. The proposed approach to generating a model image set is based on feature extraction. Features are extracted from callout images of ADR, including potential defect indication type, size and location. Experimental results show that the proposed approach is fast and a low false alarm rate with acceptable detection rate is ensured. Moreover, the approach is applicable to different blade types and varied views of the blade. Further validation shows that the approach can be applied to the update of the model image set, when more images are generated from new blades and the model becomes inaccurate for anomaly detection in the new images.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.