• The Journal of Korea Robotics Society
• /
• v.17 no.3
• /
• pp.245-254
• /
• 2022

Sensor dataset for autonomous driving is one of the essential components as the deep learning approaches are widely used. However, most driving datasets are focused on typical environments such as sunny or cloudy. In addition, most datasets deal with color images and lidar. In this paper, we propose a driving dataset with multi-spectral images and lidar in adverse weather conditions such as snowy, rainy, smoky, and dusty. The proposed data acquisition system has 4 types of cameras (color, near-infrared, shortwave, thermal), 1 lidar, 2 radars, and a navigation sensor. Our dataset is the first dataset that handles multi-spectral cameras in adverse weather conditions. The Proposed dataset is annotated as 2D semantic labels, 3D semantic labels, and 2D/3D bounding boxes. Many tasks are available on our dataset, for example, object detection and driveable region detection. We also present some experimental results on the adverse weather dataset.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2006.04a
• /
• pp.199-204
• /
• 2006

Airborne LIDAR systems have been increasingly used for various applications as an effective surveying mean that can be complementary or alternative to the traditional one based on aerial photos. A LIDAR system is a multi-sensor system consisting of GPS, INS, and a laser scanner and hence the errors associated with the LIDAR data can be significantly affected by not only the errors associated with each individual sensor but also the errors involved in combining these sensors. The analysis about these errors have been performed by some researchers but yet insufficient so that the results can be critically contributed to performing accurate calibration of LIDAR data. In this study, we thus analyze these error sources, derive their mathematical models and perform the sensitivity analysis to assess how significantly each error affects the LIDAR data. The results from this sensitivity analysis in particular can be effectively used to determine the main parameters modelling the systematic errors associated with the LIDAR data for their calibration.

• The Journal of Korea Robotics Society
• /
• v.16 no.2
• /
• pp.103-111
• /
• 2021

This study addresses a low-cost lidar sensor-based glass feature extraction method for an accurate map representation using statistical moments, i.e. the mean and variance. Since the low-cost lidar sensor produces range-only data without intensity and multi-echo data, there are some difficulties in detecting glass-like objects. In this study, a principle that an incidence angle of a ray emitted from the lidar with respect to a glass surface is close to zero degrees is concerned for glass detection. Besides, all sensor data are preprocessed and clustered, which is represented using statistical moments as glass feature candidates. Glass features are selected among the candidates according to several conditions based on the principle and geometric relation in the global coordinate system. The accumulated glass features are classified according to the distance, which is lastly represented on the map. Several experiments were conducted in glass environments. The results showed that the proposed method accurately extracted and represented glass windows using proper parameters. The parameters were empirically designed and carefully analyzed. In future work, we will implement and perform the conventional SLAM algorithms combined with our glass feature extraction method in glass environments.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.2
• /
• pp.313-320
• /
• 2018

The importance of sensors on a self-driving vehicle has rising since it act as eyes for the vehicle. Lidar sensors based on laser technology tend to yield better image quality with more laser channels, thus, it has higher detection accuracy for obstacles, pedistrians, terrain, and other vechicles. However, incorporating more laser channels results higher unit price more than ten times, and this is a major drawback for using high channel lidar sensors on a vehicle for actual consumer market. To come up with this drawback, we propose a method of integrating multiple low channel, low cost lidar sensors acting as one high channel sensor. The result uses four 16 channels lidar sensors with small form factor acting as one bulky 64 channels sensor, which in turn, improves vehicles cosmetic aspects and helps widespread of using the lidar technology for the market.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.6
• /
• pp.1099-1110
• /
• 2023

The recognition system of autonomous driving and robot navigation performs vision work such as object recognition, tracking, and lane detection after multi-sensor fusion to improve performance. Currently, research on a deep learning model based on the fusion of a camera and a lidar sensor is being actively conducted. However, deep learning models are vulnerable to adversarial attacks through modulation of input data. Attacks on the existing multi-sensor-based autonomous driving recognition system are focused on inducing obstacle detection by lowering the confidence score of the object recognition model.However, there is a limitation that an attack is possible only in the target model. In the case of attacks on the sensor fusion stage, errors in vision work after fusion can be cascaded, and this risk needs to be considered. In addition, an attack on LIDAR's point cloud data, which is difficult to judge visually, makes it difficult to determine whether it is an attack. In this study, image scaling-based camera-lidar We propose an attack method that reduces the accuracy of LCCNet, a fusion model (camera-LiDAR calibration model). The proposed method is to perform a scaling attack on the point of the input lidar. As a result of conducting an attack performance experiment by size with a scaling algorithm, an average of more than 77% of fusion errors were caused.

• Journal of the Korean Society of Hazard Mitigation
• /
• v.4 no.4 s.15
• /
• pp.55-61
• /
• 2004

Rapid developments in sensor technologies now allow the generation of multi-source topographical data. For many applications, however, the geospatial information provided by individual sensors is not complete, precise, and consistent. To solve these inherent problems, additional diverse sources of complementary data can be used and fused. In this paper, the experiment was done for generation of 3D orthoimage data using LIDAR data and digital camera image. And the results show that 3D orthoimage can be used for the flood monitoring.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.12
• /
• pp.158-164
• /
• 2015

Lane detection is one of the key parts among autonomous vehicle technologies because lane keeping and path planning are based on lane detection. Camera is used for lane detection but there are severe limitations such as narrow field of view and effect of illumination. On the other hands, Lidar sensor has the merits of having large field of view and being little influenced by illumination because it uses intensity information. Existing researches that use methods such as Hough transform, histogram hardly handle multiple lanes in the co-occuring situation of lanes and road marking. In this paper, we propose a method based on RANSAC and regularization which provides a stable and precise detection result in the co-occuring situation of lanes and road marking in highway scenarios. This is performed by precise lane point extraction using circular model RANSAC and regularization aided least square fitting. Through quantitative evaluation, we verify that the proposed algorithm is capable of multi lane detection with high accuracy in real-time on our own acquired road data.

• Journal of Korean Society for Geospatial Information Science
• /
• v.16 no.2
• /
• pp.67-76
• /
• 2008

Recently, one of the most outstanding technological characteristics of aerial survey is an application of Direct Georeferencing, which is based on the integration of main sensing sensors such as aerial camera or Lidar with positioning sensors GPS and IMU. In addition, a variety of digital aerial mapping cameras is developed and supplied with the verification of their technical superiority and applicability. In accordance with this requirement, the development of a multi-looking aerial photographing system is just making 3-D information acquisition and texture mapping possible for the dead areas arising from building side and high terrain variation where the use of traditional phptogrammetry is not valid. However, the development of a multi-looking camera integrating different sensors and multi-camera array causes some problems to conduct time synchronization among sensors and their geometric and radiometric calibration. The establishment of a test field for aerial sensor calibration is absolutely necessary to solve this problem. Therefore, this paper describes investigations for photogrammetric Test Field of foreign countries and suggest an establishment scheme for domestic test field.

• Tunnel and Underground Space
• /
• v.32 no.6
• /
• pp.451-463
• /
• 2022

Whenever a mineshaft accidentally collapses, speedy risk assessment is both required and crucial. But onsite safety diagnosis by humans is reportedly difficult considering the additional risk of collapse of the unstable mineshaft. Generally, drones equipped with high-speed lidar sensors can be used for such inspection. However, the drone technology is restrictively applicable at very shallow depth, failing in mineshafts with depths of hundreds of meters because of the limit of wireless communication and turbulence inside the mineshaft. In previous study, a three-dimensional (3D) scanning system with a single channel lidar was fabricated and operated using towed cable in a mineshaft to a depth of 200 m. The rotation and pendulum movement errors of the measuring unit were compensated for by applying the data of inertial measuring unit and comparing the similarity between the scan data of the adjacent depths (Kim et al., 2020). However, the errors grew with scan depth. In this paper, a multi-channel lidar sensor to obtain a continuous cross-sectional image of the mineshaft from a winch system pulled from bottom upward. In this new approach, within overlapped region viewed by the multi-channel lidar, rotation error was compensated for by comparing the similarity between the scan data at the same depth. The fabricated system was applied to scan 0-165 m depth of the mineshaft with 180 m depth. The reconstructed image was depicted in a 3D graph for interpretation.

• ETRI Journal
• /
• v.29 no.4
• /
• pp.411-420
• /
• 2007

The steady evolution of mapping technology is leading to an increasing availability of multi-sensory geo-spatial datasets, such as data acquired by single-head frame cameras, multi-head frame cameras, line cameras, and light detection and ranging systems, at a reasonable cost. The complementary nature of the data collected by these systems makes their integration to obtain a complete description of the object space. However, such integration is only possible after accurate co-registration of the collected data to a common reference frame. The registration can be carried out reliably through a triangulation procedure which considers the characteristics of the involved data. This paper introduces algorithms for a multi-primitive and multi-sensory triangulation environment, which is geared towards taking advantage of the complementary characteristics of spatial data available from the above mentioned sensors. The triangulation procedure ensures the alignment of involved data to a common reference frame. The devised methodologies are tested and proven efficient through experiments using real multi-sensory data.