“…In 2008, Yu-Chih Liu et al staged a PSV to obtain the complete perspective around the car [2]. After then, Mengmeng Yu et al used surround cameras to obtain a 360degree surround view in the parking guide [3]. Recently, Chunxiang Wang [4], Jae Kyu Suhr [5], Linshen LI [6] used a PSV to realize the parking slot detection in automatic parking.…”
The automatic parking is being massively developed by car manufacturers and providers. Until now, there are two problems with the automatic parking. First, there is no openly-available segmentation labels of parking slot on panoramic surround view (PSV) dataset. Second, how to detect parking slot and road structure robustly. Therefore, in this paper, we build up a public PSV dataset. At the same time, we proposed a highly fused convolutional network (HFCN) based segmentation method for parking slot and lane markings based on the PSV dataset. A surround-view image is made of four calibrated images captured from four fisheye cameras. We collect and label more than 4,200 surround view images for this task, which contain various illuminated scenes of different types of parking slots. A VH-HFCN network is proposed, which adopts an HFCN as the base, with an extra efficient VH-stage for better segmenting various markings. The VH-stage consists of two independent linear convolution paths with vertical and horizontal convolution kernels respectively. This modification enables the network to robustly and precisely extract linear features. We evaluated our model on the PSV dataset and the results showed outstanding performance in ground markings segmentation. Based on the segmented markings, parking slots and lanes are acquired by skeletonization, hough line transform and line arrangement.
“…In 2008, Yu-Chih Liu et al staged a PSV to obtain the complete perspective around the car [2]. After then, Mengmeng Yu et al used surround cameras to obtain a 360degree surround view in the parking guide [3]. Recently, Chunxiang Wang [4], Jae Kyu Suhr [5], Linshen LI [6] used a PSV to realize the parking slot detection in automatic parking.…”
The automatic parking is being massively developed by car manufacturers and providers. Until now, there are two problems with the automatic parking. First, there is no openly-available segmentation labels of parking slot on panoramic surround view (PSV) dataset. Second, how to detect parking slot and road structure robustly. Therefore, in this paper, we build up a public PSV dataset. At the same time, we proposed a highly fused convolutional network (HFCN) based segmentation method for parking slot and lane markings based on the PSV dataset. A surround-view image is made of four calibrated images captured from four fisheye cameras. We collect and label more than 4,200 surround view images for this task, which contain various illuminated scenes of different types of parking slots. A VH-HFCN network is proposed, which adopts an HFCN as the base, with an extra efficient VH-stage for better segmenting various markings. The VH-stage consists of two independent linear convolution paths with vertical and horizontal convolution kernels respectively. This modification enables the network to robustly and precisely extract linear features. We evaluated our model on the PSV dataset and the results showed outstanding performance in ground markings segmentation. Based on the segmented markings, parking slots and lanes are acquired by skeletonization, hough line transform and line arrangement.
“…Similarly, although a Harris corner detection [ 8 ] and BRIEF descriptor [ 9 ] based algorithm for images mosaicking is mentioned, not much detail was given, including the most important part of residual optimization. The authors of [ 10 ], from Delphi Automotive, proposed an image stitching method based on traditional checkerboard calibration and look-up tables (LUT). The obvious problem with this method is that a big check board is needed and the position of placement is strictly restricted.…”
Although an automatic parking system has been installed in many vehicles recently, it is still hard for the system to confirm by itself whether a vacant parking area truly exists or not. In this paper, we introduced a robust vision-based vacancy parking area detecting method for both indoor and outdoor environments. The main contribution of this paper is given as follows. First, an automatic image stitching method is proposed. Secondly, the problem of environment illuminating change and line color difference is considered and solved. Thirdly, the proposed algorithm is insensitive to the shadow and scene diversity, which means the detecting result satisfies most of the environment. Finally, a vehicle model is considered for tracking and reconfirming the detecting results to eliminate most of the false positives.
“…The parking assist system proposed here consists of a back sonar which along with the vehicle speed provides a translucent display which changes to orange when the vehicle is in motion and to red when any obstacle is encountered [3].This paper discusses about a 360 degree surround view system with parking guidance in which a judgment is made whether the area is sufficient for parking. Only if the area is sufficient the static and dynamic overlays are displayed which visually guide the host driver to the appropriate parking lot [4]. The new lane detection system uses the same rear-view camera as that used in the parking assistance system.…”
Section: Related Workmentioning
confidence: 99%
“…This node calculation involves Bezier curves, which involve cubic and quadratic equations. Selecting the parking area and deciding if the available area will be sufficient and then displaying the dynamic and static overlay [2], [4] also proves to be a wastage of resource, since computation is made twice once for calculating the sufficiency of parking space and second for displaying the static and the dynamic overlay. Instead a single dynamic overlay can be generated that has colored lines which indicate the distance of the host vehicle from the other.…”
Section: Observationsmentioning
confidence: 99%
“…For instance, the overlay can have color to indicate danger, a yellow portion to indicate the driver to proceed with caution and a green portion to indicate safe zone. A 360 degree surround view camera [4] or a rear view camera [5] can be used so that the driver gets a clear view of the environment.…”
This paper discloses an efficient method to display the vehicle trajectory for reverse parking. The major problem that inexperienced drivers face today is the difficulty in reverse parking the vehicle. To alleviate this difficulty, the proposed system has a display unit inside the vehicle which provides an overlay that indicates as to how the vehicle should be traversed. The system includes a rear view camera and a display unit which superimposes the trajectory calculated, on the image obtained from the camera. Dynamic overlay algorithm, which involves only linear equations, is developed to show the vehicle path with marked distances as the vehicle is turning during reverse. This is calculated by obtaining the steering angle from the vehicle and calculating the coordinates that should be connected by segments.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.