This paper proposes a sensor fusion-based low-cost vehicle localization system. The proposed system fuses a global positioning system (GPS), an inertial measurement unit (IMU), a wheel speed sensor, a single front camera, and a digital map via the particle filter. This system is advantageous over previous methods from the perspective of mass production. First, it only utilizes low-cost sensors. Second, it requires a low-volume digital map where road markings are expressed by a minimum number of points. Third, it consumes a small computational cost and has been implemented in a low-cost real-time embedded system. Fourth, it requests the perception sensor module to transmit a small amount of information to the vehicle localization module. Last, it was quantitatively evaluated in a large-scale database.

Even though many public parking lots are located underground and indoors, most existing automatic parking space detection and tracking methods have difficulty handling such scenarios due to severe illumination and complex obstacle conditions. To overcome this problem, this paper proposes a method that detects and tracks parking spaces in underground and indoor environments by fusing sensors already mounted on mass produced vehicles. The proposed detection method finds parking spaces based on a high-level fusion of two complementary approaches: parking slot marking-based and free space-based. Parking slots are detected by estimating parallel line pairs and free spaces are detected by recognizing the positions of parked vehicles as well as pillars. The proposed tracking method enhances the previous method by considering pillar information. Since pillars degrade parking slot tracking performance, this method estimates a pillar region and utilizes it to remove false edges and to estimate the amount of occlusion.

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.