• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.05a
• /
• pp.660-661
• /
• 2015

In this paper, we describe the output of specific situation through the recognition of several situation in the school zone based school. In the school zone, there needs the method of situation recognition to react to the diverse event or accident, and the situation output should be requested.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.05a
• /
• pp.666-667
• /
• 2015

The situation recognition can be implemented by configuring several situation in the school zone system. Such the recognized situations can use the result informing to the event through appropriate output format. In this paper, we propose the design scheme of situation output in the school zone system.

• The KIPS Transactions:PartB
• /
• v.13B no.1 s.104
• /
• pp.15-20
• /
• 2006

This paper describes research on intelligent game character through performance enhancements of physics engine in computer games. The algorithm that recognizes the physics situation uses momentum back-propagation neural networks. Also, we present an experiment and its results, integration methods that display optimum performance based on the physics situation. In this experiment on integration methods, the Euler method was shown to produce the best results in terms of fps in a simulation environment with collision detection. Simulation with collision detection was shown similar fps for all three methods and the Runge-kutta method was shown the greatest accuracy. In the experiment on physics situation recognition, a physics situation recognition algorithm where the number of input layers (number of physical parameters) and output layers (destruction value for the master car) is fixed has shown the best performance when the number of hidden layers is 3 and the learning count number is 30,000. Since we tested with rigid bodies only, we are currently studying efficient physics situation recognition for soft body objects.

• Journal of Multimedia Information System
• /
• v.9 no.1
• /
• pp.1-10
• /
• 2022

China is a big country in animal fur industry. The total production and consumption of fur are increasing year by year. However, the recognition of fur in the fur production process still mainly relies on the visual identification of skilled workers, and the stability and consistency of products cannot be guaranteed. In response to this problem, this paper proposes a feature fusion-based animal fur recognition network on the basis of typical convolutional neural network structure, relying on rapidly developing deep learning techniques. This network superimposes texture feature - the most prominent feature of fur image - into the channel dimension of input image. The output feature map of the first layer convolution is inverted to obtain the inverted feature map and concat it into the original output feature map, then Leaky ReLU is used for activation, which makes full use of the texture information of fur image and the inverted feature information. Experimental results show that the algorithm improves the recognition accuracy by 9.08% on Fur_Recognition dataset and 6.41% on CIFAR-10 dataset. The algorithm in this paper can change the current situation that fur recognition relies on manual visual method to classify, and can lay foundation for improving the efficiency of fur production technology.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.8 no.4
• /
• pp.185-194
• /
• 2013

Abstract- In distant-talking environments, speech recognition performance degrades significantly due to noise and reverberation. Recent work of Michael L. Selzer shows that in microphone array speech recognition, the word error rate can be significantly reduced by adapting the beamformer weights to generate a sequence of features which maximizes the likelihood of the correct hypothesis. In this approach, called Likelihood Maximizing Beamforming algorithm (Limabeam), one of the method to implement this Limabeam is an UnSupervised Limabeam(USL) that can improve recognition performance in any situation of environment. From our investigation for this USL, we could see that because the performance of optimization depends strongly on the transcription output of the first recognition step, the output become unstable and this may lead lower performance. In order to improve recognition performance of USL, some post-filter techniques can be employed to obtain more correct transcription output of the first step. In this work, as a post-filtering technique for first recognition step of USL, we propose to add a Wiener-Filter combined with Feature Weighted Malahanobis Distance to improve recognition performance. We also suggest an alternative way to implement Limabeam algorithm for Hidden Markov Network (HM-Net) speech recognizer for efficient implementation. Speech recognition experiments performed in real distant-talking environment confirm the efficacy of Limabeam algorithm in HM-Net speech recognition system and also confirm the improved performance by the proposed method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.11
• /
• pp.2853-2873
• /
• 2013

Over the last few years, one of the most common purposes of smart homes is to provide human centric services in the domain of u-healthcare by analyzing inhabitants' daily living. Currently, the major challenges in activity recognition include the reliability of prediction of each classifier as they differ according to smart homes characteristics. Smart homes indicate variation in terms of performed activities, deployed sensors, environment settings, and inhabitants' characteristics. It is not possible that one classifier always performs better than all the other classifiers for every possible situation. This observation has motivated towards combining multiple classifiers to take advantage of their complementary performance for high accuracy. Therefore, in this paper, a method for activity recognition is proposed by optimizing the output of multiple classifiers with Genetic Algorithm (GA). Our proposed method combines the measurement level output of different classifiers for each activity class to make up the ensemble. For the evaluation of the proposed method, experiments are performed on three real datasets from CASAS smart home. The results show that our method systematically outperforms single classifier and traditional multiclass models. The significant improvement is achieved from 0.82 to 0.90 in the F-measures of recognized activities as compare to existing methods.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.14 no.2
• /
• pp.128-133
• /
• 2021

Currently, autonomous vehicle markets are commercializing a third-level autonomous vehicle, but there is a possibility that an accident may occur even during fully autonomous driving due to stability issues. In fact, autonomous vehicles have recorded 81 accidents. This is because, unlike level 3, autonomous vehicles after level 4 have to judge and respond to emergency situations by themselves. Therefore, this paper proposes a vehicle crisis detection system(VCDS) that collects and stores information outside the vehicle through CNN, and uses the stored information and vehicle sensor data to output the crisis situation of the vehicle as a number between 0 and 1. The VCDS consists of two modules. The vehicle external situation collection module collects surrounding vehicle and pedestrian data using a CNN-based neural network model. The vehicle crisis situation determination module detects a crisis situation in the vehicle by using the output of the vehicle external situation collection module and the vehicle internal sensor data. As a result of the experiment, the average operation time of VESCM was 55ms, R-CNN was 74ms, and CNN was 101ms. In particular, R-CNN shows similar computation time to VESCM when the number of pedestrians is small, but it takes more computation time than VESCM as the number of pedestrians increases. On average, VESCM had 25.68% faster computation time than R-CNN and 45.54% faster than CNN, and the accuracy of all three models did not decrease below 80% and showed high accuracy.

• Journal of Korea Multimedia Society
• /
• v.15 no.3
• /
• pp.312-322
• /
• 2012

The paper presents an approach for recognizing the broken area of the traffic signs. The method is based on the Recognition System for Traffic Signs (RSTS). This paper describes an approach to using the location histogram matching for the broken traffic signs recognition, after the general process of the image detection and image categorization. The recognition proceeds by using the SIFT matching to adjust the acquired image to a standard position, then the histogram bin will be compared preprocessed image with reference image, and finally output the location and percents value of the broken area. And between the processing, some preprocessing like the blurring is added in the paper to improve the performance. And after the reorganization, the program can operate with the GPS for traffic signs maintenance. Experimental results verified that our scheme have a relatively high recognition rate and a good performance in general situation.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.24 no.6
• /
• pp.627-634
• /
• 2016

In this paper, an augmented video generation method to evaluate the performance of lane departure warning system is proposed. In our system, the input is a video which have road scene with general clean lane, and the content of output video is the same but the lane is synthesized with contamination image. In order to synthesize the contamination lane image, two approaches were used. One is example-based image synthesis, and the other is background-based image synthesis. Example-based image synthesis is generated in the assumption of the situation that contamination is applied to the lane, and background-based image synthesis is for the situation that the lane is erased due to aging. In this paper, a new contamination pattern generation method using Gaussian function is also proposed in order to produce contamination with various shape and size. The contamination lane video can be generated by shifting synthesized image as lane movement amount obtained empirically. Our experiment showed that the similarity between the generated contamination lane image and real lane image is over 90 %. Futhermore, we can verify the reliability of the video generated from the proposed method through the analysis of the change of lane recognition rate. In other words, the recognition rate based on the video generated from the proposed method is very similar to that of the real contamination lane video.

• Journal of Platform Technology
• /
• v.8 no.4
• /
• pp.11-19
• /
• 2020

In an autonomous driving environment, dynamic recognition of objects is essential as the situation changes in real time. In addition, as the number of sensors and control modules built into an autonomous vehicle increases, the amount of data the central control unit has to process also rapidly increases. By minimizing the output data from the sensor, the load on the central control unit can be reduced. This study proposes a dynamic object recognition algorithm solely using the embedded processor on a LiDAR sensor. While there are open source algorithms to process the point cloud output from LiDAR sensors, most require a separate high-performance processor. Since the embedded processors installed in LiDAR sensors often have resource constraints, it is essential to optimize the algorithm for efficiency. In this study, an embedded processor based object recognition algorithm was developed for autonomous vehicles, and the correlation between the size of the point clouds and processing time was analyzed. The proposed object recognition algorithm evaluated that the processing time directly increased with the size of the point cloud, with the processor stalling at a specific point if the point cloud size is beyond the threshold