This paper proposes an end-to-end trainable one-stage parking slot detection method for around view monitor (AVM) images. The proposed method simultaneously acquires global information (entrance, type, and occupancy of parking slot) and local information (location and orientation of junction) by using a convolutional neural network (CNN), and integrates them to detect parking slots with their properties. This method divides an AVM image into a grid and performs a CNN-based feature extraction. For each cell of the grid, the global and local information of the parking slot is obtained by applying convolution filters to the extracted feature map. Final detection results are produced by integrating the global and local information of the parking slot through non-maximum suppression (NMS). Since the proposed method obtains most of the information of the parking slot using a fully convolutional network without a region proposal stage, it is an end-to-end trainable one-stage detector. In experiments, this method was quantitatively evaluated using the public dataset (PS2.0) and outperforms previous methods by showing both recall and precision of 99.77%, type classification accuracy of 100%, and occupancy classification accuracy of 99.31% while processing 60 frames per second.

This paper proposes a method that automatically calibrates four cameras of an around view monitor (AVM) system in a natural driving situation. The proposed method estimates orientation angles of four cameras composing the AVM system, and assumes that their locations and intrinsic parameters are known in advance. This method utilizes lane markings because they exist in almost all on-road situations and appear across images of adjacent cameras. It starts by detecting lane markings from images captured by four cameras of the AVM system in a cost-effective manner. False lane markings are rejected by analyzing the statistical properties of the detected lane markings. Once the correct lane markings are sufficiently gathered, this method first calibrates the front and rear cameras, and then calibrates the left and right cameras with the help of the calibration results of the front and rear cameras. This two-step approach is essential because side cameras cannot be fully calibrated by themselves, due to insufficient lane marking information. After this initial calibration, this method collects corresponding lane markings appearing across images of adjacent cameras and simultaneously refines the initial calibration results of four cameras to obtain seamless AVM images. In the case of a long image sequence, this method conducts the camera calibration multiple times, and then selects the medoid as the final result to reduce computational resources and dependency on a specific place. In the experiment, the proposed method was quantitatively and qualitatively evaluated in various real driving situations and showed promising results.

An automatic parking system is an essential part of autonomous driving, and it starts by recognizing vacant parking spaces. This paper proposes a method that can recognize various types of parking slot markings in a variety of lighting conditions including daytime, nighttime, and underground. The proposed method can readily be commercialized since it uses only those sensors already mounted on off-the-shelf vehicles: an around-view monitor (AVM) system, ultrasonic sensors, and in-vehicle motion sensors. This method first detects separating lines by extracting parallel line pairs from AVM images. Parking slot candidates are generated by pairing separating lines based on the geometric constraints of the parking slot. These candidates are confirmed by recognizing their entrance positions using line and corner features and classifying their occupancies using ultrasonic sensors. For more reliable recognition, this method uses the separating lines and parking slots not only found in the current image but also found in previous images by tracking their positions using the in-vehicle motion-sensor-based vehicle odometry. The proposed method was quantitatively evaluated using a dataset obtained during the day, night, and underground, and it outperformed previous methods by showing a 95.24% recall and a 97.64% precision.

Although it is well-known that the two-stage approach outperforms the one-stage approach in general object detection, they have similarly performed in parking slot detection so far. We consider this is because the two-stage approach has not yet been adequately specialized for parking slot detection. Thus, this paper proposes a highly specialized two-stage parking slot detector that uses region-specific multi-scale feature extraction. In the first stage, the proposed method finds the entrance of the parking slot as a region proposal by estimating its center, length, and orientation. The second stage of this method designates specific regions that most contain the desired information and extracts features from them. That is, features for the location and orientation are separately extracted from only the specific regions that most contain the locational and orientational information. In addition, multi-resolution feature maps are utilized to increase both positioning and classification accuracies. A high-resolution feature map is used to extract detailed information (location and orientation), while another low-resolution feature map is used to extract semantic information (type and occupancy). In experiments, the proposed method was quantitatively evaluated with two large-scale public parking slot detection datasets: SNU and PS2.0 datasets. In SNU dataset, the proposed method achieved state-of-the-art performance with 95.75% recall and 95.78% precision.

This paper presents a method for simplifying and quantizing a deep neural network (DNN)-based object detector to embed it into a real-time edge device. For network simplification, this paper compares five methods for applying channel pruning to a residual block because special care must be taken regarding the number of channels when summing two feature maps. Based on the comparison in terms of detection performance, parameter number, computational complexity, and processing time, this paper discovers the most satisfying method on the edge device. For network quantization, this paper compares post-training quantization (PTQ) and quantization-aware training (QAT) using two datasets with different detection difficulties. This comparison shows that both approaches are recommended in the case of the easy-to-detect dataset, but QAT is preferable in the case of the difficult-to-detect dataset. Through experiments, this paper shows that the proposed method can effectively embed the DNN-based object detector into an edge device equipped with Qualcomm’s QCS605 System-on-Chip (SoC), while achieving a real-time operation with more than 10 frames per second.