In this chapter, we introduce how the proposed BHF is adopted to detect the vacant parking spaces in a typical outdoor parking lot. Nowadays, using an intelligent surveillance system to manage parking lots has become practical. A recent technology review about smart parking system can be found in [67]. To assist users to efficiently find a vacant parking space, an intelligent parking space management system can not only provide the total number of vacant spaces in the parking lot but also explicitly identify the location of vacant parking spaces. In addition, a vision-based system may provide many value-added services, like parking space guidance and video surveillance.
In practice, the major challenges of vision-based parking space detection come
from occlusion effect, shadow effect, perspective distortion, and the fluctuation of lighting condition. In Fig. 18, we show several parking lot images in our dataset. In these images, some environmental factors are mixed together in a sophisticated way.
For instance, the illumination in a sunny day is quite different from that in a cloudy day; a parked car may occlude or cast a shadow over the parking space next to it; a shadowed region may be mistakenly recognized as a dark-colored vehicle; and a light-colored vehicle under strong sunlight may look very similar to a vacant parking space.
(a)
(b)
(c)
Morning Noon Evening
Fig. 18. Image shots of a parking lot. (a) Captured in a normal day. (b) Captured in a day with strong sunlight. (c) Captured in a cloudy day.
Up to now, several methods have been proposed to overcome the aforementioned difficulties. These methods can be roughly classified into two major categories:
car–driven and space-driven. For a car–driven method, cars are the major target and algorithms are developed to detect cars. Based on the result of car detection, vacant parking spaces are determined. To detect objects of interest, plentiful object detection
algorithms can be used. For example, the object detection method proposed in [68] by Schneiderman and Kanade is a trainable detector based on the statistics of localized parts. The adaboosting-based detection algorithm [69] is another widely used technique for the detection of specific objects in 2-D images. The method proposed by Felzenszwalb et al. [32] offered an efficient way to match objects based on a part-based model that well represents an object by pictorial structures. A global color-based model had been proposed by Tsai et al. [13] to efficiently detect vehicle candidates. On the other hand, Lee et al. [70] and Masaki [71] kept tracking and recording the movement of vehicles to identify empty parking spaces. Even though these object detection based frameworks had gained impressive achievement in many circumstances, such as highway and roadway, most of these algorithms are not specifically designed for vacant parking space detection in a typical parking lot. For example, as shown in Fig. 18, the captured images may include some cars with unclear details. Besides, due to the perspective distortion, a car far away from the camera only occupies a small area in the captured image. This perspective distortion may also affect the performance of car detection.
For a space-driven method, the property of a vacant parking space is the major focus and available parking spaces are detected directly. When the camera is static, several background subtraction algorithms, like [2], can be used to detect foreground objects. Typically, these algorithms assume the variation of the background is statistically stationary within a short period. Unfortunately, this assumption is not always true for an outdoor scene. For example, a passing cloud that block the sunlight may suddenly change the lightness. To handle the dynamic variation of an outdoor environment, a possible solution is to build a complete background reference set under all kinds of lighting conditions. Funck et al. [11] proposed an eigen-space
space and computational cost. With a suitable background model, a typical way to determine the status of a parking space is to check the ratio of foreground pixel number to background pixel number. However, even if the background model is well learned, this kind of method still suffers from the occlusions and shadows caused by neighboring cars. To improve the performance of detection, Huang et al. [46]
proposed a Bayesian detection framework to take into account both ground plane model and car model. Both occlusion effect and illumination variation were modeled under that framework. Recently, Bong et al. [72] proposed a Car Park Occupancy Information System (COINS) by using a “bi-stream” detector to overcome the shadow effect. In their approach, one stream used the background subtraction method to perform car detection, while the other stream adopted edge information to achieve shadow-insensitive detection. By using an “And” operator to combine both detection results, detection performance was improved.
On the other hand, some other space-driven methods assume a vacant parking space possesses homogeneous appearance and use this property to detect vacant spaces. For example, Yamada and Mizuno [73] designed a homogeneity measure by calculating the area of fragmental segments. In principle, a vacant space has fewer but larger segments, while the area of a parked car has an opposite property. Lee et al. [74]
suggested an entropy-based metric to determine the status of each parking space.
However, these two systems ignored the shadow and occlusion caused by adjacent cars. In [75], Fabian used a segment-based homogeneity measure similar to that in [73]
and proposed a method for occlusion handling. By pre-training a weighting map to indicate the image regions that may get occupied by neighboring cars, the influence of the occlusion effect can be reduced. Even thought their homogeneity measure is effective for most parking spaces, the environmental variations, especially the shadow effect and the over-exposure effect caused by strong sunlight, may fail the assumption
of homogeneous appearance. In practice, the shadow effect makes a parking space less homogeneous while the over-exposure effect makes the appearance of a car more homogeneous.
Some other authors tried to detect vacant parking spaces via classification. For example, Dan [76] trained a general support vector machine (SVM) classifier by directly using the cascaded color vectors inside a parking space as the classification feature. However, the occlusion patterns were not well modeled in their approach. On the other hand, Wu et al. [77] grouped three neighboring spaces as a unit and define the color histogram across three spaces as the feature in their SVM classifier. With this arrangement, the inter-space correlation can be learned beforehand to overcome the inter-occlusion problem. However, the performance of classification is greatly affected by the environmental variations. In general, the lighting changes may cause the variations of object appearance in both brightness and chromaticity. This effect may dramatically degrade the accuracy of classification-based detection.
The rest of this chapter is organized as follows. In Section 4.2, we present the main idea of our algorithm. The top-down information from the 3-D scene model is detailed in Section 4.3, while the message from image observation is presented in Section 4.4. The whole inference procedure is explained in Section 4.5. Experimental results and discussions are presented in Section 4.6.