• ETRI Journal
• /
• 제42권4호
• /
• pp.491-504
• /
• 2020

We present AB9, a neural processor for inference acceleration. AB9 consists of a systolic tensor core (STC) neural network accelerator designed to accelerate artificial intelligence applications by exploiting the data reuse and parallelism characteristics inherent in neural networks while providing fast access to large on-chip memory. Complementing the hardware is an intuitive and user-friendly development environment that includes a simulator and an implementation flow that provides a high degree of programmability with a short development time. Along with a 40-TFLOP STC that includes 32k arithmetic units and over 36 MB of on-chip SRAM, our baseline implementation of AB9 consists of a 1-GHz quad-core setup with other various industry-standard peripheral intellectual properties. The acceleration performance and power efficiency were evaluated using YOLOv2, and the results show that AB9 has superior performance and power efficiency to that of a general-purpose graphics processing unit implementation. AB9 has been taped out in the TSMC 28-nm process with a chip size of 17 × 23 ㎟. Delivery is expected later this year.

• 국제학술발표논문집
• /
• The 8th International Conference on Construction Engineering and Project Management
• /
• pp.455-462
• /
• 2020

Noise which is unwanted sound is a serious pollutant that can affect human health, as well as the working and living environment if exposed to humans. However, current noise management on the construction project is generally conducted after the noise exceeds the regulation standard, which increases the conflicts with inhabitants near the construction site and threats to the safety and productivity of construction workers. To overcome the limitations of the current noise management methods, the activities of construction equipment which is the main source of construction noise need to be managed throughout the construction period in real-time. Therefore, this paper proposed a framework for automatically detecting noise sources in construction sites in real-time based on convolutional neural networks (CNNs) according to the following four steps: (i) Step 1: Definition of the noise sources; (ii) Step 2: Data preparation; (iii) Step 3: Noise source classification using the audio CNN; and (iv) Step 4: Noise source detection using the visual CNN. The short-time Fourier transform (STFT) and temporal image processing are used to contain temporal features of the audio and visual data. In addition, the AlexNet and You Only Look Once v3 (YOLOv3) algorithms have been adopted to classify and detect the noise sources in real-time. As a result, the proposed framework is expected to immediately find construction activities as current noise sources on the video of the construction site. The proposed framework could be helpful for environmental construction managers to efficiently identify and control the noise by automatically detecting the noise sources among many activities carried out by various types of construction equipment. Thereby, not only conflicts between inhabitants and construction companies caused by construction noise can be prevented, but also the noise-related health risks and productivity degradation for construction workers and inhabitants near the construction site can be minimized.

• 반도체디스플레이기술학회지
• /
• 제23권2호
• /
• pp.1-5
• /
• 2024

In the electronics industry, a lot of research and development is being conducted on electronic component supply, component alignment and insertion, and automation of soldering on the back side of the PCB for automatic PCB assembly. Additionally, as the use of electronic components increases in the automotive component field, there is a growing need to automate the alignment and insertion of components with leads such as transistors, coils, and fuses on PCB. In response to these demands, the types of PCB and parts used have been more various, and as this industrial trend, the quantity and placement of automation equipment that supplies, aligns, inserts, and solders components has become important in PCB manufacturing plants. It is also necessary to reduce the pre-setting time before using each automation equipment. In this study, we propose a method in which a vision system recognizes the type of component and simultaneously corrects alignment errors during the process of aligning and inserting various types of electronic components. The proposed method is effective in manufacturing various types of PCBs by minimizing the amount of automatic equipment inserted after alignment with the component supply device and omitting the preset process depending on the type of component supplied. Also the advantage of the proposed method is that the structure of the existing automatic insertion machine can be easily modified and utilized without major changes.

• 대한토목학회논문집
• /
• 제43권5호
• /
• pp.667-674
• /
• 2023

건물에서 재난이 발생할경우, 건물 내 인원을 신속히 구조하여 사상자를 최소화하는 것은 단연 최우선순위가 된다. 이러한 구조활동을 위해서는 건물내 어디에 몇 명이 있는지를 알아야 하는데, 실시간으로 알기가 어렵다보니 주로 건물주나 경비원 등 관계자의 진술이나 층별 면적, 수용 인원과 같은 기초자료에 의존하는 실정이다. 따라서 빠르고 정확하게 재실인원 정보를 파악하여 현장에 대한 불확실성을 낮추고 골든타임내 효율적인 구조활동을 지원하는 것이 반드시 필요하다. 본 연구는 컴퓨터 비전 알고리즘을 활용하여 이미 건물에 설치되어 있는 여러대의 CCTV 가 촬영한 이미지 로부터 건물 위치별 재실인원을 계수하는 방법론을 제시한다. 계수 방법론은 (1)카메라별 관심선(LOI) 설정을 통한 다중카메라 네트워크 환경구축, (2)딥러닝을 활용한 모니터링 구역내 사람 탐지 및 추적, (3)다중 카메라 네트워크 환경을 고려한 인원 합산 세단계로 구성된다. 제안된 방법론은 5층 건물을 대상으로 세 개의 시간대 별로 수행된 현장 실험을 통해 검증되었다. 최종 결과는 89.9%의 정확도로 재실자를 인식하는 것으로 나타났으며, 층별, 구역별 합산결과도 93.1%, 93.3%의 정확도로 우수했다. 층별 평균MAE와 RMSE는 각각 0.178과 0.339이었다. 이 처럼 실시간으로 제공하는 건물내 재실자 정보는 초기 재난 대응단계에 신속하고 정확한 구조활동을 지원 할 수있다.