Performance Enhancement Algorithm using Supervised Learning based on Background Object Detection for Road Surface Damage Detection

2019 ◽  
Vol 18 (3) ◽  
pp. 95-105
Author(s):  
Seungbo Shim ◽  
◽  
Chanjun Chun ◽  
Seung-Ki Ryu
Keyword(s):  
Object Detection ◽  
Damage Detection ◽  
Supervised Learning ◽  
Performance Enhancement ◽  
Surface Damage ◽  
Road Surface ◽  
Background Object ◽  
Enhancement Algorithm

scholarly journals Road Surface Damage Detection Using Fully Convolutional Neural Networks and Semi-Supervised Learning

Sensors ◽  
2019 ◽  
Vol 19 (24) ◽  
pp. 5501 ◽  
Author(s):  
Chanjun Chun ◽  
Seung-Ki Ryu
Keyword(s):  
Neural Networks ◽  
Damage Detection ◽  
Supervised Learning ◽  
Convolutional Neural Networks ◽  
Surface Damage ◽  
Road Surface ◽  
Training Dataset ◽  
The Road ◽  
Fully Convolutional Neural Networks ◽  
On The Road

The various defects that occur on asphalt pavement are a direct cause car accidents, and countermeasures are required because they cause significantly dangerous situations. In this paper, we propose fully convolutional neural networks (CNN)-based road surface damage detection with semi-supervised learning. First, the training DB is collected through the camera installed in the vehicle while driving on the road. Moreover, the CNN model is trained in the form of a semantic segmentation using the deep convolutional autoencoder. Here, we augmented the training dataset depending on brightness, and finally generated a total of 40,536 training images. Furthermore, the CNN model is updated by using the pseudo-labeled images from the semi-supervised learning methods for improving the performance of road surface damage detection technique. To demonstrate the effectiveness of the proposed method, 450 evaluation datasets were created to verify the performance of the proposed road surface damage detection, and four experts evaluated each image. As a result, it is confirmed that the proposed method can properly segment the road surface damages.

scholarly journals Computer Vision-Based Bridge Damage Detection Using Deep Convolutional Networks with Expectation Maximum Attention Module

Sensors ◽  
2021 ◽  
Vol 21 (3) ◽  
pp. 824
Author(s):  
Wenting Qiao ◽  
Biao Ma ◽  
Qiangwei Liu ◽  
Xiaoguang Wu ◽  
Gang Li
Keyword(s):  
Damage Detection ◽  
Complex Structure ◽  
Surface Damage ◽  
Break Point ◽  
Convolutional Networks ◽  
Concrete Crack ◽  
Current State ◽  
Bridge Damage ◽  
Bridge Inspections ◽  
Impact Problems

Cracks and exposed steel bars are the main factors that affect the service life of bridges. It is necessary to detect the surface damage during regular bridge inspections. Due to the complex structure of bridges, automatically detecting bridge damage is a challenging task. In the field of crack classification and segmentation, convolutional neural networks have offer advantages, but ordinary networks cannot completely solve the environmental impact problems in reality. To further overcome these problems, in this paper a new algorithm to detect surface damage called EMA-DenseNet is proposed. The main contribution of this article is to redesign the structure of the densely connected convolutional networks (DenseNet) and add the expected maximum attention (EMA) module after the last pooling layer. The EMA module is obviously helpful to the bridge damage feature extraction. Besides, we use a new loss function which considers the connectivity of pixels, it has been proved to be effective in reducing the break point of fracture prediction and improving the accuracy. To train and test the model, we captured many images from multiple bridges located in Zhejiang (China), and then built a dataset of bridge damage images. First, experiments were carried out on an open concrete crack dataset. The mean pixel accuracy (MPA), mean intersection over union (MIoU), precision and frames per second (FPS) of the EMA-DenseNet are 87.42%, 92.59%, 81.97% and 25.4, respectively. Then we also conducted experiments on a more challenging bridge damage dataset, the MIoU, where MPA, precision and FPS were 79.87%, 86.35%, 74.70% and 14.6, respectively. Compared with the current state-of-the-art algorithms, the proposed algorithm is more accurate and robust in bridge damage detection.

scholarly journals Penilaian Kondisi Jalan Poros Sabbang Selatan Menggunakan Metode Surface Distress Index

2021 ◽  
Vol 6 (1) ◽  
pp. 24
Author(s):  
Dewi Artika Sari ◽  
Afdal Kisman
Keyword(s):  
Surface Damage ◽  
Road Surface ◽  
Assessment System ◽  
Pavement Condition ◽  
Surface Conditions ◽  
Traffic Volumes ◽  
Surface Distress ◽  
Left Section ◽  
The Right ◽  
Initial Research

Prasarana jalan jika terbebani volume lalu lintas yang tinggi dan berulang-ulang akan menyebabkan terjadinya penurunan kualitas jalan sehingga dapat mempengaruhi keamanan, kenyamanan dan kelancaran dalam berlalu lintas. Untuk menjaga agar tidak terjadi penurunan kondisi khususnya pada jalan poros Kecamatan Sabbang Selatan Kabupaten Luwu Utara tepatnya di jalan Padang Sarre, Buntu Terpedo sampai jalan Dandang sepanjang 4 km perlu adanya penanganan. Maka perlu dilakukan penelitian awal terhadap kondisi permukaan jalan dengan melakukan survei secara visual dengan cara menganalisa kerusakan berdasarkan jenis dantingkat kerusakannya. Tujuan penelitian yaitu menilai kondisi perkerasan danpenanganan sesuai kondisi permukaan jalan. Penelitian ini menggunakan system penilaian kondisi perkerasan menurut Bina Marga dengan perhitungan Surface Distress Index (SDI) untuk jalan beraspal. Dari hasil penelitian di dapatkan penilaian untuk jenis kerusakan permukaan jalan pada ruas kanan yaitu retak pinggir 1,183%, lubang 0,031%, amblas 0,054%, retak kulit buaya 3,271%, retak kotak-kotak 3,222%, tambalan 0,033% dan pengelupasan butir 0,013%. Sedangkan untuk ruas kiri yaitu retak pinggir 0,035%, lubang 0,051%, amblas 0,000%, retak kulit buaya 0,130%, retak kotak-kotak 2,351%, tambalan 0,000% dan pengelupasan butir 0,150%. Kondisi perkerasan jalan yang menjadi objek penelitian sepanjang 4 km yaitu 85% baik, 0% sedang, 15% rusak ringan, 0% rusakberat.Road infrastructure if it is burdened by high and repetitive traffic volumes will cause a decrease in road quality so that it can affect safety, comfort and smoothness in traffic. To prevent deterioration in conditions, especially on the axis road of South Sabbang District, North Luwu Regency, precisely on Padang Sarre road, Buntu Terpedo to Dandang road along 4 km, it needs handling. So it is necessary to conduct an initial research on road surface conditions by conducting a visual survey by analyzing the damage based on the type and level of damage. The research objective was to assess pavement conditions and handling according to road surface conditions. This study uses a pavement condition assessment system according to Bina Marga with the calculation of the Surface Distress Index (SDI) for asphalt roads. From the research results obtained an assessment for the type of road surface damage on the right side, namely edge cracks 1.183%, holes 0.031%, collapse 0.054%, crocodile skin cracks 3.271%, checkered cracks 3.222%, 0.033% patches and 0.013% peeling grains. Whereas for the left section, the edges cracked 0.035%, holes 0.051%, collapsed 0.000%, crocodile skin cracks 0.130%, checkered cracks 2.351%, fillings 0.000% and peeling 0.150%. The condition of the pavement which is the object of the research along 4 km is 85% good, 0% moderate, 15% lightly damaged, 0% heavily damaged.

Sign in / Sign up

Export Citation Format

Share Document