*Geographic Information Systems in Geospatial Intelligence*

checkerboard, with 30 mm square fields, a set of close-up RGB/IR images of the checkerboard placed in different positions and orientations (**Figure 3(a)**), can be collected and used for calibration. The Bouguet's Camera Calibration Toolbox [44] in MATLAB can be used for the identification of RGB and IR camera parameters, utilizing the two versions of Herrera's method [45]. IR camera calibration, the IR emitter should be disabled during imaging so as to achieve appropriate light conditions. The output matrices for the intrinsic, distortion and extrinsic calibration parameters are presented in **Table 2**.

available for the Kinect, online. For each input disparity map *i*, the plane corners are extracted, defining a polygon. For each point x*<sup>d</sup>* inside the polygon, the corresponding disparity *<sup>d</sup>* is used for computing a depth value z*<sup>d</sup>* using z <sup>¼</sup> <sup>1</sup>

*On the Use of Low-Cost RGB-D Sensors for Autonomous Pothole Detection with Spatial…*

where *d* ¼ *du* since the measured disparities are used, and *c*<sup>0</sup> and *c*<sup>1</sup> are part of the

3D X*<sup>c</sup>* points originating a 3D point cloud. To each 3D point cloud, a plane is fitted

As a pre-processing step and prior to the segmentation and clustering of the RGB

Since the data collected comprises of pothole and non-pothole pavement defect image frames, the first preprocessing step after the calibration is to eliminate the non-pothole images from the database. Using unsupervised classification on the acquired RGB data frames, images with potential potholes are selected based on *k*means clustering [46], and adaptive median filtering. From the candidate potholes images, edge lines are estimated and the corresponding ellipse(s) are fitted using least squares optimization. This algorithm is applied in a batch processing mode, and the efficiency of the approach is then confirmed by using visual inspection and

Integral projection (IP) has the discriminative to accumulate and resolve the pixel histograms into pothole and non-potholes pixels, by analyzing the horizontal and vertical (HV) pixel distributions within an image, represented by horizontal and vertical projections. Given a grayscale image *I*(*x, y*), the horizontal and vertical

HP ð Þ¼ *<sup>y</sup>* <sup>X</sup>

VP ð Þ¼ *<sup>x</sup>* <sup>X</sup>

where HP and VP are the horizontal and vertical IP, respectively. *xy* and *yx* denote the set of horizontal pixels at the vertical pixel *y* and the set of vertical pixels

*3.4.3 Database search for candidate pothole image frames using ellipse fitting and HVIP*

With a visual comparison of 99% efficiency for the pothole database search, **Table 3** shows the results using the pothole search engine (PSE). The ellipse detection indicates the presence of defect or no-defect within the image, and also defines the orientation of the pothole with respect to the longitudinal profile of the road.

*i* ∈*xy*

*j*∈*yx*

and depth data, pothole search engine (PSE) is necessary. It is then possible to extract potholes-only images for further autonomous processing. This can be accomplished by using a 2-class *k*-means clustering of the candidate RGB image frames, and is confirmed using ellipsoidal fitting on the classified binary image

depth camera's intrinsics. The correspondences *xd; yd; zd*

*3.4.1* k*-means clustering and edge ellipse fitting for pothole search*

*3.4.2 Horizontal and vertical integral projection (HVIP)*

IPs are defined as follows in Eqs. (15) and (16).

at the horizontal pixel *x*, respectively.

using a standard total least squares algorithm.

*DOI: http://dx.doi.org/10.5772/intechopen.88877*

**3.4 Pothole search engine**

frame.

comparison.

**157**

*c*1*du*þ*c*<sup>0</sup> ,

� � are used for computing

*I i*ð Þ *; j* (15)

*I i*ð Þ *; y* (16)
