• Transactions of the Korean Society of Automotive Engineers
• /
• v.20 no.3
• /
• pp.113-118
• /
• 2012

Collision detection plays a key role in collision mitigation system. The malfunction of the collision mitigation system can result in another dangerous situation or unexpected feeling to driver and passenger. To prevent this situation, the collision time, offset, and collision decision should be determined from the appropriate collision detection algorithm. This study focuses on a method to determine the time to collision (TTC) and frontal offset (FO) between the ego vehicle and the target object. The path prediction method using the ego vehicle information is proposed to improve the accuracy of TTC and FO. The path prediction method utilizes the ego vehicle motion data for better prediction performance. The proposed algorithm is developed based on laser scanner. The performance of the proposed detection algorithm is validated in simulations and experiments.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.10
• /
• pp.3608-3626
• /
• 2021

The detection of bolts is an important task in high-speed train inspection systems, and it is frequently performed to ensure the safety of trains. The difficulty of the vision-based bolt inspection system lies in small sample defect detection, which makes the end-to-end network ineffective. In this paper, the problem is resolved in two stages, which includes the detection network and cascaded classification networks. For small bolt detection, all bolts including defective bolts and normal bolts are put together for conducting annotation training, a new loss function and a new boundingbox selection based on the smallest axis-aligned convex set are proposed. These allow YOLOv3 network to obtain the accurate position and bounding box of the various bolts. The average precision has been greatly improved on PASCAL VOC, MS COCO and actual data set. After that, the Siamese network is employed for estimating the status of the bolts. Using the convolutional Siamese network, we are able to get strong results on few-shot classification. Extensive experiments and comparisons on actual data set show that the system outperforms state-of-the-art algorithms in bolt inspection.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.11 no.3
• /
• pp.163-171
• /
• 2016

Lane detection is a widely researched topic. Although simple road detection is easily achieved by previous methods, lane detection becomes very difficult in several complex cases involving noisy edges. To address this, we use a Convolution neural network (CNN) for image enhancement. CNN is a deep learning method that has been very successfully applied in object detection and recognition. In this paper, we introduce a robust lane detection method based on a CNN combined with random sample consensus (RANSAC) algorithm. Initially, we calculate edges in an image using a hat shaped kernel, then we detect lanes using the CNN combined with the RANSAC. In the training process of the CNN, input data consists of edge images and target data is images that have real white color lanes on an otherwise black background. The CNN structure consists of 8 layers with 3 convolutional layers, 2 subsampling layers and multi-layer perceptron (MLP) of 3 fully-connected layers. Convolutional and subsampling layers are hierarchically arranged to form a deep structure. Our proposed lane detection algorithm successfully eliminates noise lines and was found to perform better than other formal line detection algorithms such as RANSAC

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.50-50
• /
• 2000

In this paper, a new measuring system is :proposed which can measure the fine 6-DOF displacement of rigid bodies. Its measurement principle is based on detection of laser beam reflected from a specially fabricated mirror that looks like a triangular pyramid having an equilateral cross-sectional shape. The mirror has three lateral reflective surfaces inclined 45$^{\circ}$ to its bottom surface. We call this mirror 3-facet mirror. The 3-facet mirror is mounted on the object whose 6-DOF displacement is to be measured. The measurement is operated by a laser-based optical system composed of a 3-facet mirror, a laser source, three position-sensitive detectors(PSD). In the sensor system, three PSDs are located at three corner points of a triangular formation, which is an equilateral triangular formation tying parallel to the reference plane. The sensitive areas of three PSDs are oriented toward the center point of the triangular formation. The object whose 6-DOF displacement is to be measured is situated at the center with the 3-facet mirror on its top surface. A laser beam is emitted from the laser source located at the upright position and vertically incident on the top of the 3-fatcet mirror. Since each reflective facet faces toward each PSD, the laser beam is reflected at the 3-facet mirror and splits into three sub-beams, each of which is reflected from the three facets and finally arrives at three PSDs, respectively. Since each PSD is a 2-dimensional sensor, we can acquire the information on the 6-DOF displacement of the 3-facet mirror. From this principle, we can get 6-DOF displacement of any object simply by mounting the 3-facet mirror on the object. In this paper, we model the relationship between the 6-DOF displacement of the object and the outputs of three PSDs. And, a series of simulations are performed to demonstrate the effectiveness of the proposed method. The simulation results show that the proposed sensing system can be an effective means of obtaining 3-dimensional position and orientation of arbitrary objects.

• 제어로봇시스템학회:학술대회논문집
• /
• 1995.10a
• /
• pp.174-177
• /
• 1995

Detecting a small threat object either fast moving or floating on shallow water presents a formidable challenge to shipboard sensor systems, which must determine whether or not to launch defensive weapons in a timely manner. An integrated multisensor concept is envisioned wherein the combined use of active and passive sensor is employed for the detection of short duration targets in dense ocean surface clutter to maximize detection range. The objective is to develop multisensor integration techniques that operate on detection data prior to track formation while simultaneously fusing contacts to tracks. In the system concept, detections from a low grazing angle search radar render designations to a sensor-search infrared sensor for target classification which in turn designates an active electro-optical sensor for sector search and target verification.

• Journal of KIISE
• /
• v.42 no.1
• /
• pp.138-143
• /
• 2015

In this paper we develop a novel human action recognition system based on communication between an ear-mounted Bluetooth camera and an action recognition server to aid scene recognition for the blind. First, if the blind capture an image of a specific location using the ear-mounted camera, the captured image is transmitted to the recognition server using a smartphone that is synchronized with the camera. The recognition server sequentially performs human detection, object detection and action recognition by analyzing human poses. The recognized action information is retransmitted to the smartphone and the user can hear the action information through the text-to-speech (TTS). Experimental results using the proposed system showed a 60.7% action recognition performance on the test data captured in indoor and outdoor environments.

• Current Optics and Photonics
• /
• v.6 no.2
• /
• pp.151-160
• /
• 2022

Fundus images can reflect ocular diseases and systemic diseases such as glaucoma, diabetes mellitus, and hypertension. Thus, research on fundus-detection equipment is of great importance. The fundus camera has been widely used as a kind of noninvasive detection equipment. Most existing devices can only obtain two-dimensional (2D) retinal-image information, yet the fundus of the human eye also has spectral characteristics. The fundus has many pigments, and their different distributions in the eye lead to dissimilar tissue penetration for light waves, which can reflect the corresponding fundus structure. To obtain more abundant information and improve the detection level of equipment, a snapshot nonmydriatic fundus imaging spectral system, including fundus-imaging spectrometer and illumination system, is studied in this paper. The system uses a microlens array to realize snapshot technology; information can be obtained from only a single exposure. The system does not need to dilate the pupil. Hence, the operation is simple, which reduces its influence on the detected object. The system works in the visible and near-infrared bands (550-800 nm), with a volume less than 400 mm × 120 mm × 75 mm and a spectral resolution better than 6 nm.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.10 no.2
• /
• pp.13-20
• /
• 2014

In this paper, we implemented the object scanning with nxtOSEK which is an open source platform. nxtOSEK consists of device driver of leJOS NXJ C/Assembly source code, TOPPERS/ATK(Automotive real time Kernel) and TOPPERS/JSP Real-Time Operating System source code that includes ARM7 specific porting part, and glue code make them work together. nxtOSEK can provide ANSI C by using GCC tool chain and C API and apply for real-time multi tasking features. We experimented the 3D scanning with ultra sonic and laser sensor which are made directly by laser module diode and experimented the measurement of scanning the object by knowing x, y, and z coordinates for every points that it scans. In this paper, the laser module is the dimension of $6{\times}10[mm]$ requiring 5volts/5[mW], and used the laser light of wavelength in the 650[nm] range. For detecting the object, we used the beacon detection algorithm and as the laser light swept the objects, the photodiode monitored the ambient light at interval of 10[ms] which is called a real time. We communicated the 3D scanning platform via bluetooth protocol with host platform and the results are displayed via DPlot graphic tool. And therefore we enhanced the functionality of the 3D scanner for identifying the image scanning with laser sensor modules compared to ultra sonic sensor.

• Spatial Information Research
• /
• v.21 no.3
• /
• pp.11-19
• /
• 2013

Compared with traditional video monitoring systems that provide a video-recording function as a main service, an intelligent video monitoring system is capable of extracting/tracking objects and detecting events such as car accidents, traffic congestion, pedestrian detection, and so on. Thus, the object tracking is an essential function for various intelligent video monitoring and surveillance systems. In this paper, we propose a background and local histogram-based object tracking approach for intelligent video monitoring systems. For robust object tracking in a live situation, the result of optical flow and local histogram verification are combined with the result of background subtraction. In the proposed approach, local histogram verification allows the system to track target objects more reliably when the local histogram of LK position is not similar to the previous histogram. Experimental results are provided to show the proposed tracking algorithm is robust in object occlusion and scale change situation.

• Journal of IKEEE
• /
• v.25 no.1
• /
• pp.76-82
• /
• 2021

In this paper, the compressed sensing basic pursuit denoise algorithm adopted to synthetic aperture radar imaging is investigated to improve the object recognition. From the incomplete data sets for image processing, the compressed sensing algorithm had been integrated to recover the data before the conventional back- projection algorithm was involved to obtain the synthetic aperture radar images. This method can lead to the reduction of measurement events while scanning the objects. An ultra-wideband radar scheme using a stripmap synthetic aperture radar algorithm was utilized to detect objects hidden behind the box. The Ultra-Wideband radar system with 3.1~4.8 GHz broadband and UWB antenna were implemented to transmit and receive signal data of two conductive cylinders located inside the paper box. The results confirmed that the images can be reconstructed by using a 30% randomly selected dataset without noticeable distortion compared to the images generated by full data using the conventional back-projection algorithm.