Vehicle detection using morphological image processing technique

Vehicle density information for traffic regulation including the timing of traffic lights is still very minimal. This study aims to calculate the number of vehicles at an intersection then classify the density level of each road segment. The detection process begins with taking video from Teling intersection of Manado City, Indonesia. Video processed using the Gaussian Mixture Model (GMM) algorithm and Morphological Operation (MO) to detect vehicles object in the form of BLOB (Binary Large Object). The results of the feature extraction are calculated to get the number of vehicles from the specified Region of Interest (ROI). The results of counting vehicles are classified according to the density level to be able to compare the level of congestion on each road segment. The results of the proposed system accuracy is 90.9% for the calculation of vehicles on the road. This research is expected to be implemented in Smart Traffic Light.

show abstract

“…Morphological operations involve two-pixel arrays. The first array is a morphologically processed image and the second array is the kernel [15].…”

Section: Morphological Operationmentioning

confidence: 99%

Vehicle Detection and Counting to Identify Traffic Density in The Intersection of Road Using Image Processing

Lahinta¹,

Zainuddin²,

Syarif³

2019

Proceedings of the 1st International Conference on Science and Technology, ICOST 2019, 2-3 May, Makassar, Indonesia

View full text Add to dashboard Cite

show abstract

“…The image transforming is carried out at three levels: crude pictures, region level, and vehicle level. Ajmal and Hussain [4] come up with a new and proficient algorithm build on image processing utilizing elevated cams for vehicle locating and classification solely in highways. The algorithm utilizes thresholding and edge detection methods for the vehicle reorganization.…”

Section: Introductionmentioning

confidence: 99%

Classify vehicles: Classification or clusterization?

Thota

Badawy

Changalasetty

et al. 2015

2015 International Conference on Circuits, Power and Computing Technologies [ICCPCT-2015]

View full text Add to dashboard Cite

Vehicle classification has crop up as an important field of study due of its importance in variety of applications like surveillance, security framework, traffic congestion prevention and accidents avoidance. The image sequences for traffic scenes are recorded by a stationary NI smart camera. The video clip is processed in LabVIEW to detect vehicle and measure characteristics like width, length, area, perimeter using image process feature extraction techniques. Data mining is the use of automated data analysis techniques to uncover previously undetected relationships among data items. Two of the major data mining techniques are classification and clustering. To classify a vehicle as big or small needs to classify vehicles into classes. Among many, two techniques in WEKA are feed-forward neural network (NN) classification technique and k-means clustering techniques. To choose between the two techniques is a challenging task. We carry experiments using the extracted features of vehicles from traffic video with both techniques and found that classification model out-performed cluster model by a small degree.

show abstract

“…Citra foreground yang merupakan objek terdeteksi kemudian diproses agar menghasilkan objek kendaraan. Agar objek kendaraan dapat diolah dengan baik maka mesti dilakukan transformasi morfologi pada citra tersebut [4]. Objek kendaraan dari tiap frame video citra jalan akan dihubungkan sehingga menghasilkan garis pergerakan kendaraan.…”

unclassified

Penghitung Trafik Kendaraan Berbasis Object Recognition Studi Kasus Jalan Utama Universitas Tanjungpura

Ananda,

Sholva,

Nyoto

2022

JEPIN

View full text Add to dashboard Cite

Pertumbuhan penggunaan kendaraan bermotor untuk transportasi oleh masyarakat terus meningkat seiring waktu. Sebagai lembaga pendidikan tinggi dengan jumlah mahasiswa aktif mencapai angka 31 ribu orang maka Universitas Tanjungpura perlu menyadari bagaimana penggunaan jalan oleh pengendara kendaraan bermotor di Universitas Tanjungpura dalam bagian dari perencanaan pembangunannya untuk menghindari permasalahan yang mungkin timbul dikemudian hari. Penelitian ini bertujuan untuk menghasilkan suatu sistem yang dapat menghitung trafik kendaraan di jalan masuk utama Universitas Tanjungpura. Peneliti menggunakan pendekatan object recognition untuk mengetahui jenis kendaraan yang lewat apakah merupakan kendaraan sepeda motor atau mobil, dimana digunakan metode background subtraction dan pemrosesan morfologi dalam tugas deteksi objek, dan metode Haar cascade classifier dalam tugas klasifikasi jenis kendaraan dari objek yang terdeteksi. Pada penelitian ini dilatih model klasifikasi kendaraan sepeda motor (masuk dan keluar) dengan masing-masing 5000 data latih dan model klasifikasi kendaraan mobil (masuk dan keluar) dengan masing-masing 500 data latih. Evaluasi pendeteksi objek menunjukkan bahwa program dapat mendeteksi objek yang bergerak dengan akurasi dengan akurasi terendah sebesar 67% dan akurasi tertinggi sebesar 93%. Evaluasi model klasifikasi kendaraan menunjukkan nilai F1-score rata-rata 0.916 (sepeda motor masuk), 0.311 (mobil masuk), 0.965 (sepeda motor keluar) dan 0.427 (mobil keluar). Evaluasi menunjukkan tidak terdapat pengaruh yang signifikan mengenai perbedaan kondisi waktu dan kepadatan trafik kendaraan terhadap performa model klasifikasi kendaraan. Di mana nilai rata-rata f1-score pada pengujian pagi, siang dan sore adalah masing-masing 68%, 62% dan 67% dan rata-rata akurasi pada pengujian padat, sedang dan sepi adalah masing-masing 89%, 86% dan 88%. Hasil pengujian unit testing dan integration testing menunjukkan sistem ini dapat mendeteksi objek kendaraan yang lewat, mengetahui jenis kendaraan tersebut dan menghitung jumlahnya serta menyediakan cara untuk mendapatkan data trafik kendaraan yang dihasilkan. Secara keseluruhan penelitian dinilai berhasil dalam membuat sebuah sistem penghitung trafik kendaraan berbasis object recognition studi kasus jalan utama Universitas Tanjungpura.

show abstract

Vehicle detection using morphological image processing technique

Cited by 17 publications

References 3 publications

Vehicle Detection and Counting to Identify Traffic Density in The Intersection of Road Using Image Processing

Vehicle Detection and Counting to Identify Traffic Density in The Intersection of Road Using Image Processing

Classify vehicles: Classification or clusterization?

Penghitung Trafik Kendaraan Berbasis Object Recognition Studi Kasus Jalan Utama Universitas Tanjungpura

Contact Info

Product

Resources

About