Algorithmsfor Automatic ParkingSharath Panduraj Baliga,Automotivesoftware engineering,TU –Chemnitz ,Chemnitz,Germany.Email: [email protected] Abstract— The automactic parking system is one amongmost researched topics to help the drivers to park their vehicle with ease evenin the narrow paths and make the parking management systems simple for theincreasing number of vehicles in the major cities.It is very helpful for thedrivers if there is some system which informs them about the available parkingspace in the parking area.This paper provides the walk through to the variousavailable algorithms for automatic parking system.
The ideas behind everyalgorithm which concentrate on development of different stages of the automaticparking are discussed. Keywords: AVM-Around View Monitor, LSD – Line segment detector,RGB – Red Green and Blue. —————————— u ——————————1 IntroductionParkingis a very difficult task even for a skilled driver because of limited space,incoming vehicles, and fixed and moving obstacles such as pedestrians.Therefore, the development of parking assistant systems and autonomous parkingsystems is important. Furthermore, an autonomous vehicle must perform numeroustasks to safely park the vehicle in a narrow space, including precise environmentdetection and parking manoeuvres 5,18.
TheAutomatic parking also helps in reduction of traffic problems, since the 20% ofall the congestion in the major cities are caused by frustrated drivers drivingaround the block searching for parking spaces 14. Many automatic parking systems have been proposedthatmaximize both the safety and convenience ofparking. Target position designation is one of the primary components of an automaticparking system. Perception methods to detectavailable parking spaces are categorized into twotypes: freespace-based approaches 2-5and parking slot marking-based approaches 6-15 Therest of this paper is organised as follows: Section-2 gives the important areasof concentration for automatic parking, Section-3 will brief about state ofart, Section-4 discusses about the various algorithm and the concepts, Section-5concludes the paper and Section-6 gives the future scope.2 Important Stepsin Automatic Parking:a. Detectingthe free parking plot.b. Pathplanning.
c. Controllingthe steering input and velocity of the vehicle (Including accelerating orbraking to track the desired trajectory). 5,18 3 State of art:Acommercial version of automatic parallel parking was introduced by Toyota MotorCorporation in Toyota Prius in 2004. Lexus also debuted a car, the 2007 LS,with an Advanced Parking Guidance System17, while the detection of parkingslot was done using ultrasonic sensors and now it’s been evolved and replacedby vision based detection.Theparking system has evolved from semi-automatic to automatic, up to the levelwhere the parking can be done with the help of remote control or the mobile appin latest BMW cars.
4 4 AutomaticParking Algorithms:4.1 AutomaticParking Employing Swarm Algorithm. Generation of shortest possible pathtrajectory for the parallel parking with one shot track according to the dimensionsof the car.A fuzzy controller is designed to decidethe driving velocity and the required steering angle. The fish swarm search algorithm is used tosearch for fuzzy controller parameters and the parking time that achieve bestpath tracking.12.
4.2 Apath-planning algorithm for parallel automatic parking. The method overcomes the followingdrawbacks of previous researchesThe path generation using clothoid curvewhere it’s difficult to approximate holonomic path by smooth non-holonomic pathwhich may cause more operations in the parking process.8,13Motion generation with trigonometricfunction that plans a continuous and iterative path. But the parking spaceshould be larger than other method to avoid moving forward and backward toomany times.6,7This method gives an iterativepath-planning algorithm to park in the narrow space which is not big enough tooperate parking in one time.19 4.
3 A Trajectory Planning Method Based on ForwardPath Generation and Backward Tracking Algorithm. Assuming the free parking plot is detected,this algorithm plans for generation of parking path from a desired startingpoint and the heading angle to the destination with referred heading angle inthe parking lot.15The algorithm plans the backward trajectory by a forward path headingout from parking to the desired position on the road.9The forward path is implemented by dividing the path in to two segments(locating segment and the entering segment) .9The arc in the locating segment and the Bezier curve in the enteringsegment are connected together. The arc can consider the minimum distance betweenthe front corner of the vehicle and a static obstacle using the geometricmodel.1This algorithm can be applied to both parallel parking and theperpendicular parking. 4.
4 A Benchmark and a Learning-Based Approachfor Visual based Parking slot detection A large scale parking slot image databaseis established and for each image in the database marking points and parkingslots are carefully labelled, this database is used as benchmark to detect theparking slot.10 While in learning based approach, for thegiven test image the marking points will be detected first and then validparking slots can be inferred. 10 4.
5 Parking Slot Detection Based on Around ViewMonitor (AVM) Systems. Detecting the parking slot with the help ofvision based approach i.e. around view monitor offers 360 degrees surroundingvehicle view by summing up all the images obtained by 4 fisheye cameras locatedat centre of front bumpers, rear trunk lid and each of the side B-pillar.16 This method utilizes line segment detector(LSD) to detect parking slot marking lines which have parallel line pair andthis method of detection is found to be faster.
It also overcomes the drawbackof most of the vision based approach for parking slot detection while detectingthe parking spot where the markings are damaged.2,3 Location of cameras in AVM system.4.6 Automaticparking space detection.This system helps the drivers tohave an idea about the free parking space in the parking yard so that the timein searching for the free space will be reduced. The algorithm forthe same is as follows:a. System will get Livestreamvideo of the parking lot from camera.b.
Images are captured when a carenters or leaves the parking lot.c. RGB Images are converted tograyscale images.d. Do calibration i. Select the coordinates of the parking lot.Thiswill crop the extra space other than parking lot from the image. ii.
Select the coordinates of the single parkingslot. This will divide the parking lot into equal size slots.e. Each block is converted fromgrayscale to binary and then inverse binary to get the car in white color and parkingarea into black color.f. Threshold value is calculatedin every block to detect whether that block contain car or not.g.
If value is less than thresholdvalue than that block is free and available for parking car and if value isgreater than block is occupied.5 Conclusion.There are different algorithms to realizeautomatic parking system.
The parking slot detection can be done by ultrasonicor visual based methods, but the visual based method overcomes some of thedrawbacks like dependencies where the method using ultrasonic sensors requiresthe reference object behind the vehicle to fetch the path.11Most of the parkingalgorithm uses fuzzy logic control to tract the path towards the parking slot.Each algorithm looks like a better approach overcomingthe drawbacks of the past researches. Hence research under automatic parkingsystem still exists and works towards the development of more smooth andreliable parking system. 6. FutureScopeIn future this paper work can be taken as benchmarkand convert in to a research work on the specific area in automatic parkingsystems. AknowledgmentResearch forums like IEEE explorer andGoogle Scholar are the main sources for the research papers referred in thispaper.
References1 Bae, II, etal. “Path Generation and Tracking Based on a Bezier Curve for a SteeringRate Controller of Autonomous Vehilcles.” Intelligent TransportationSystems-(lTSC), 2013. C.
Wang, H. Zhang, M. Yang, X. Wang, L. Ye, and C. Guo, “Automaticparkingbased on a bird’s eye view vision system,” Adv.
Mech. Eng., vol.2014,pp. 1–13, Dec. 2014. 2Gioi R G,Jakubowicz J, Morel J M, et al.
“LSD: a line segment detector”. ImageProcessing On Line, vol. 2, no. 4, pp. 35-55, 2012.
3Gioi R G, JakubowiczJ, Morel J M, et al. “LSD: A fast line segment detector with a false detectioncontrol”. IEEE transactions on pattern analysis and machine intelligence,vol.32, no. 4, pp. 722-732, 2010. H. G.
Jung, D. S. Kim, P. J. Yoon, and J.
H. Kim, “3D vision system fortherecognition of free parking site location,” Int. J.
Autom. Technol., vol.7,no. 3, pp. 361–367, May 2006 4Internethttp://www.
bmw.co.uk/en_GB/topics/ownership/connecteddrive/driver-assistance/intelligent-parking.html 5Idris, M. Y.1., et al.
“Car Park System: A Review of Smart Parking System and itsTechnology.” Information Technology Journal 8.2,2009.
6I. E.Paromtchik and C. Laugier, “Autonomous parallel parking of a nonholonomicvehicle”, in Proc. IEEE Intelligent Vehicles Symp.
,Tokyo, Japan, Sep. 1999, pp.13–18. 7I. E.Paromtchik, and C.
Laugier, “Motion Generation and Control for Parking anAutonomous Vehicle,” Proc. of the IEEE Int. Conj.
On Robotics and Automation,Minneapolis, USA, April 22-28, 1996, pp.3117-3122. 8J.P.Laumond, P.E.
Jacobs, M.Taix, R.M.Murray, “A motion planner for nonholonomicmobile robots”, IEEE Trans. Robot. Autom.
, 1994,10, (5), pp. 577–593 9JaeyoungMoon, II Bae, Jae-gwang Cha and Shiho Kim “A Trajectory Planning MethodBased on Forward Path Generation and Backward Tracking Algorithm for AutomaticParking Systems” 2014 Intelligent Transportation Systems (ITSC) October8-11,2014. Qingdao, China Jung,H.G., Kim, D.
S., Yoon, P.J., Kim, J., “Parking slot markingsrecognitionfor automatic parking assist system,” IEEE IntelligentVehiclesSymposium, pp. 106-113, June 2006. 10Linshen Li,Lin Zhang1, Xiyuan Li, Xiao Liu, Ying Shen and Lu Xiong “Vision-BasedParking-Slot Detection: A Benchmark And A Learning-Based Approach” IEEE InternationalConference on Multimedia and Expo (ICME) 2017 11LeiLi, Changle Li, Qieshi Zhang,Tao Guo and Zhifang Miao “Automatic Parking SlotDetection Based on Around View Monitor (AVM) Systems “2017 9th InternationalConference on Wireless Communications and Signal Processing (WCSP) 12MohamedHana.
fy*, Mostafa M Gomaa, Mohamed Taher, Ayman M Wahba .” Path Generation andTracking for Car Automatic Parking Employing Swarm Algorithm” The 2011International Conference on Computer Engineering & Systems, Nov. 292011-Dec. 1 2011 13MULLER B.,DEUTSCHER J., GRODDE S, “Continuous curvature trajectory design and feed forwardcontrol for parking a car”, IEEE Trans. Control Syst.
Technol., 2007, 15, (3),pp. 541–553 Nazia Bibi, Muhammad Nadeem Majid ,Hassan Dawood, and Ping guo. “Automatic Parking Space Detection System” , 2nd International Conference on Multimedia and Image Processing,2017 14SarthakMendiratta, Debopam Dey, Deepika Rani Sona “Automatic Car Parking System withVisual Indicator along with IoT” 2017 International conference on MicroelectronicDevices, Circuits and Systems (ICMDCS) 15Satonaka,Hisashi, et al. “Development of parking space detection using anultrasonic sensor.” Proc. 13th World Congr. Intell.
Transp.Syst. Serv.,1-10,2006. S. H.Jeong, C.
G. Choi, J. N. Oh, P. J. Yoon, B.
S. Kim, M. Kim, and K.H.
Lee, “Low cost design of parallel parking assist system based on anultrasonicsensor,” Int. J. Autom. Technol., vol. 11, no.
3, pp. 409–416,Jun.2010.
16Suhr J K,Jung H G. “Fully-automatic recognition of various parking slot markings inAround View Monitor (AVM) image sequences”,2012. 17Tsung-huaHsu, Jing-Fu Liu, Pen-Ning Yu, Wang-Shuan Lee and Jia-Sing Hsu .” Developmentof an Automatic Parking Systemfor Vehicle”.IEEE Vehicle Power and Propulsion Conference (VPPC), September 3-5, 2008,Harbin, China. 18Wada,Massaki, Kang Sup Yoon, and Hideki Hashimoto.
“Development of advancedparking assistance system.” Industrial Electronics, IEEE Transactions on 50.1,4-17, 2003.
19ZhenjiLv, Linhui Zhao, Zhiyuan Liu “A path-planning algorithm for parallel automaticparking “Third International Conference on Instrumentation, Measurement,Computer, Communication and Control ,2013.