Roads performs a main role in the socio-economicprogress of the country. Road transportation is faster, morefavorable and more adaptable. As studying the existing methodsa pothole is a structural in a road surface, usually asphaltpavement, due to water in the underlying soil structure andtraffic passing over the affected area. Water first incapacitatethe underlying soil; traffic then exhaust and breaks the poorlysupported asphalt surface in the affected area. Ongoing trafficoperations ejects both asphalt and the underlying soil materialto create a hole in the pavement.
Detecting potholes is one ofimportant tasks for determining proper strategies of asphalt-surfaced pavement maintenance and rehabilitation. However,manually discovering and judging methods are expensive andtime-consuming. In this paper we are discussing various existingpothole detection methods to accurately and efficiently detectpotholes.
For the transportation purpose roads plays an importantrole. Road system of a nation should be well organizedin order to develop economic and social welfare. Sinceroads have a great influence on people’s lives, aftercare andmanagement of roads should be done regularly. However,due to lack of financial resources, many local governmentare not able to conduct sufficient inspections.
Serious road accidentscan happen as a direct result, especially on those roads wherevehicle speeds are greater. The existing pothole detectionmethods are divided into three: Vibration-Based detectionmethods,3D reconstruction-based methods and vision-basedmethods. Taking the graph of road accidents occurred inIndia from the year of 2000 to 2013 are shown in Fig1. Pothole is defined as a hollow depression in the surface ofroad and minimum plan dimension is 150 mm. Potholes canproduce damages such as flat tire and wheel damage, impactand damage on the lower part of a vehicle, sudden brakingand steering wheel operation, and vehicle collision and majoraccidents. Fig. 2. Classification of pothole detection methodsII.
This method employ current data acquisition hardware todevelop a vibration-based system for initial evaluation ofpavement conditions. The pavement distress such as cracksand rutting impose impacting forces on the vehicle. Thesurface conditions of pavement can be measured from therecorded responses of the testing vehicle when driving onthe pavement. The advantage of this detection system is ofsmall storage requirement, cost-effective and amenable formanageable real-time data processing. An extensive roadnetwork in Sri Lanka that spans the country and newroads are being build every day, yet even the roads arenot maintained properly in the capital city. Vibration-basedmethod use accelerometers in order to detect potholes. Avibration based system has the advantages of, these methodsrequire small storage and can be used in real-time processing. However, this methods could provide incorrect results thatthe hinges and joints of road can be identify as potholes. Potholes that are present in the center of a lane cannot bedetected using accelerometers due to no hit by any of thevehicles wheels(Erikson et al.)
The classification of 3D reconstruction methods can befurther into three methods that are 3D laser scanner meth-ods,stereo vision methods, visualization using MicrosoftKinect sensor. A. 3D laser scanner methodsThe main idea behind the technique used by 3D laserscanner is that employs reflected laser pulses to createaccurate digital models of existing objects. The accurate 3D point cloud focused with their elevationswere captured during scanning. Then extracted focusing onspecific distress features by means of a grid-based processingapproach is discussed in the study by Chang et al. For3D laser points the segmentation method is dedicated tothe features for road pavements such as to automate thepotholes identification.
For obtaining a regular grid for thispurpose TIN-based interpolation was employed. Althoughdata quality would lose somehow after the process, regulargrid was deemed appropriate and adopted for subsequentprocessing. For reducing noises Mean filter was applied tothe grid. Afterwards,to extract the target features such aspotholes, topographic, hydraulic, and texture features areapplied. Finally, to integrate the pixels of similar features intoregions, and thus, to obtain the area sizes of each potholes,clustering method is used. An ongoing, ease assessment framework to identify troublehighlights, for example, rutting, pushing proposed by Liet al. Potholes utilizing rapid 3D transverse checkingprocedures comprising of an infrared laser line projector anda computerized camera in the proposed technique. To enhance the precision of the framework, a multi-seecoplanar plan is utilized in the alignment strategy.
With thegoal that more element focuses can be utilized and circulatedover the field of perspective of the camera. Potholes can be recognize progressively utilizing Laserfiltering frameworks. In any case, the expense of laserfiltering gear is as yet huge at vehicle-level and as of nowthese works are centered around the neighborhood exactnessof 3D estimation. B. Stereo Vision MethodsTwo advanced cameras are utilized to cover an asphaltsurface in this strategy. To break down 2D pictures fromevery one of the two cameras to distinguish and characterizeany splits is the initial step. The outcome from analyzingtwo image sources of the same pavement are then combinedso that cracks missed by one analysis are still checked. Inthis way strategy potentially accomplishing higher accuracy. Also, the pair of images on the similar asphalt surface isutilized to establish 3D surface model with longitudinaland transverse profiles through geometric modeling. Thesequence of steps such as camera calibration, distortioncorrect, matching stereo points, 3D reconstruct, and profilereport should be performed, to recover the 3D propertiesfrom given pairs of 2D images on the similar asphalt surface. Hou et al. presented a strategy of applying the stereovision technique into pavement imaging to recreate the 3Dasphalt surface surface from a pair of images.
A total offour cameras were used in two pairs to collect pavementsurface images across a 4-meter wide pavement (each pairof images covers 2 meters of the road). In this technique, 4 stages are alignment, bending modification, coordinatingand 3D remaking was included. As field tries, the road section was measured on a local roadswith the length of 650m. Stereo vision strategies requirea high computational attempt to reproduce asphalt surfacethrough the system of matching feature focuses between twoperspectives. So it is hard to utilize them in an ongoingsituation. Also, both cameras should be vary accuratelyadjusted since the cameras may misalign and affect thequality of the result if there is the vibration by the vehiclemovement. The stereo vision techniques for the measurementof pavement condition with a stereo vision system attachedto a vehicle for recording of the road network conditionssuggested by Staniek.
3D reconstruction methods fordetecting potholes are shown in fig 4. C. Kinect SensorA low-cost sensor system using Kinect sensor and a high-speed USB camera to detect and analyze potholes proposedby Joubert et al. Recently, a low-cost Kinect sensorto collect the pavement depth images and calculate theapproximate volume of a pothole discussed by Moazzamet al. The pavement depth images were collected fromconcrete and asphalt roads Using a low-cost Kinect sensor. For better visualization of potholes Meshes were generated. Area of pothole was analyzed with respect to depth. Although it is cost effective as compared toindustrial cameras and lasers, the use of infrared technologybased on Kinect sensor for measurement is still a novel ideaand further research is necessary for improvement in errorrate.
A method for automated pothole detection in asphaltpavement images proposed by Koch and Brilakis. Underthis method, the image is first segmented into defect and non-defect regions. According to the geometric characteristicsof a defect region, the potential pothole shape is thenapproximated. Next, with the texture of the surrounding non-defect region, the texture of a potential region is extractedand compared. The region of interest is assumed to bepothole, if the texture of the defect region is coarser andgrainier than the one of the surrounding surface. It wasimplemented in MATLAB utilizing the Image ProcessingToolbox for the testing purpose. Using a remote-controlledrobot vehicle prototype equipped with a HP Elite Autofocus. Webcam images were cropped from video files capturedwhich was installed at an altitude of about 2 feet.
A new unsupervised vision-based method which does notrequire expensive equipment, additional filtering and trainingphase proposed by Buza et al. Here uses image pro-cessing and spectral clustering for identification and roughestimation of potholes. B. Video-Based ApproachesIt cannot determine the magnitude of potholes for assess-ment since 2D image-based approaches have been focusedon only pothole detection and is limited to single frame. Torecognize a pothole and calculate total number of potholesover a sequence of frames Video-based approaches wereproposed. A method of 3D sparse reconstruction discussedby Golparvar-Fard et al, and 3D dense reconstructionand mesh modeling was based on the dense 3D point cloudreconstruction of Golparvar-Fard et al. The method wasvalidated on several actual potholes using a Canon Vixia HDcamera. A method for automated detection and assessment of pot-holes, where cracks and patches from video clips of Indianhighways is presented by Lokeshwor et al. Here firstcaptured video clips are segmented automatically into twodifferent types of frames category. The frames with distressand frames without distress using DFS algorithm.
Then,database of frames with distress is processed with CD-DMC algorithm. Koch et al. presented an enhanced pothole-recognition method in order to complement and improvethe previous method, which updates the texture signaturefor intact pavement regions and utilize vision tracking totrack detected potholes over a sequence of frames. Thetexture-comparison performance was increased by 53%, andthe computation time was reduced by 57% compared withthe previous method. Here assumed that only one potholeenters the viewport at a time, and therefore additional workis needed for considering multiple potholes in the viewport. Vision-based methods methods for detecting potholes areshown in fig 5. Fig. 5. Vision-based methods for detecting potholes
Detecting potholes accurately is one of crucial tasks fordetermining proper strategies of pavement maintenance. Butthe person manually detecting and evaluating methods arecostly and time-consuming. Vibration-based methods, 3Dreconstruction-based methods, and vision-based methods arethe main division of the existing pothole detection methods. So from the study, the vision-based methods are cost-effective compared to 3D laser scanner methods, it maybe difficult to accurately detect a pothole by the discussedmethods. Due to the misrepresent signal generated by noisesince they detect a pothole through analysis of the collectedimage and video data. Therefore, it is need to developa pothole detection method using different features in 2Dimages which improve the present pothole detection methodand can accurately detect a pothole.
Disclaimer: This essay has been submitted by a student. This is not an example of the work written by our professional essay writers. You can order our professional work here.
Sorry, copying is not allowed on our website. If you’d like this or any other sample, we’ll happily email it to you.
Your essay sample has been sent.
Want us to write one just for you? We can custom edit this essay into an original, 100% plagiarism free essay.Order now