Jiun-In Guo

Prof. Jiun-In Guo

National Yang Ming Chiao Tung University, Hsinchu, Taiwan
orcid

Research Focus & Metrics

Academic Career Length

22Years (2005-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 December 2020 in IEEE Transactions on Components, Packaging and Manufacturing Technology
Verified
Journal Article
Closed access
YLYu-Ting Li
Yu-Ting Li
PKPaul Kuo
Paul Kuo
JGJiun-In Guo
Jiun-In Guo
A deep ensemble Convolutional Neural Network (CNN) model to inspect Printed Circuit Board (PCB) board Dual in-line Package (DIP) soldering defects with Hybrid-YOLOv2 (YOLOv2 as a foreground detector and ResNet-101 as a classifier) and FRRF (Faster RCNN with ResNet-101 and FPN) achieved a detection rate of 97.45% and a false alarm rate (FAR) of 20-30% in the previous study [35]. However, applying the method to other production lines, environmental variations such as lighting, orientations of the sample feeds, and mechanical deviations, led to the degradation in detection performance. This paper proposes an effective self-adaption method that collects “exception data” as the samples with which the AI model made mistakes from the AOI inference edge to the training server, retraining with exceptions on the server and deploying back to the edge. The proposed defect detection system has been verified with real tests that achieved a detection rate of 99.99% with an FAR 20-30%, and less than 15 seconds of inspection time on a resolution 7296×6000 PCB image. The proposed system has proven capable of shortening inspection and repair time for online operators, where 33% efficiency boost from the three production lines of the collaborated factory has been reported [6]. The contribution of the proposed retraining mechanism is threefold: (1) Because the retraining process directly learns from the exceptions, the model can quickly adapt to the characteristic of each production line, leading to a fast and reliable mass-deployment. (2) The proposed retraining mechanism is a necessary self-service for conventional users as it incrementally improves the detection performance without professional guidance or fine-tuning. (3) The semi-automatically exception data collection method helps to lessen the time-consuming manual labeling during the retraining process.

31 December 2023 in Sensors
Verified
Journal Article
Open access
PDF file
VSVinay Malligere Shivanna
Vinay Malligere Shivanna
JGJiun-In Guo
Jiun-In Guo
Advanced driver assistance systems (ADASs) are becoming increasingly common in modern-day vehicles, as they not only improve safety and reduce accidents but also aid in smoother and easier driving. ADASs rely on a variety of sensors such as cameras, radars, lidars, and a combination of sensors, to perceive their surroundings and identify and track objects on the road. The key components of ADASs are object detection, recognition, and tracking algorithms that allow vehicles to identify and track other objects on the road, such as other vehicles, pedestrians, cyclists, obstacles, traffic signs, traffic lights, etc. This information is then used to warn the driver of potential hazards or used by the ADAS itself to take corrective actions to avoid an accident. This paper provides a review of prominent state-of-the-art object detection, recognition, and tracking algorithms used in different functionalities of ADASs. The paper begins by introducing the history and fundamentals of ADASs followed by reviewing recent trends in various ADAS algorithms and their functionalities, along with the datasets employed. The paper concludes by discussing the future of object detection, recognition, and tracking algorithms for ADASs. The paper also discusses the need for more research on object detection, recognition, and tracking in challenging environments, such as those with low visibility or high traffic density.

2 March 2023 in Sensors
Verified
Journal Article
Open access
PDF file
JLJia-Jheng Lin
Jia-Jheng Lin
JGJiun-In Guo
Jiun-In Guo
VSVinay Malligere Shivanna
Vinay Malligere Shivanna
Ssu-Yuan ChangSsu-Yuan Chang
Ssu-Yuan Chang
This paper proposes a deep learning-based mmWave radar and RGB camera sensor early fusion method for object detection and tracking and its embedded system realization for ADAS applications. The proposed system can be used not only in ADAS systems but also to be applied to smart Road Side Units (RSU) in transportation systems to monitor real-time traffic flow and warn road users of probable dangerous situations. As the signals of mmWave radar are less affected by bad weather and lighting such as cloudy, sunny, snowy, night-light, and rainy days, it can work efficiently in both normal and adverse conditions. Compared to using an RGB camera alone for object detection and tracking, the early fusion of the mmWave radar and RGB camera technology can make up for the poor performance of the RGB camera when it fails due to bad weather and/or lighting conditions. The proposed method combines the features of radar and RGB cameras and directly outputs the results from an end-to-end trained deep neural network. Additionally, the complexity of the overall system is also reduced such that the proposed method can be implemented on PCs as well as on embedded systems like NVIDIA Jetson Xavier at 17.39 fps.

26 March 2021 in IEEE Access
Verified
Journal Article
Open access
CLChun-Yu Lai
Chun-Yu Lai
BWBo-Xun Wu
Bo-Xun Wu
VSVinay Malligere Shivanna
Vinay Malligere Shivanna
JGJiun-In Guo
Jiun-In Guo
This paper presents a lightweight Multi-task Semantic Attention Network (MTSAN) to collectively deal with object detection as well as semantic segmentation aiding real-time applications of the Advanced Driver Assistance Systems (ADAS). This paper proposes a Semantic Attention Module (SAM) that introduces the semantic contextual clues from a segmentation subnet to guide a detection subnet. The SAM significantly boosts up the detection performance and computational cost by considerably decreasing the false alarm rate and it is completely independent of any other parameters. The experimental results show the effectiveness of each component of the network and demonstrate that the proposed MTSAN yields a better balance between accuracy and speed. Following the post-processing methods, the proposed module is tested and proved for its accuracy in the Lane Departure Warning System (LDWS) and Forward Collision Warning System (FCWS). In addition, the proposed lightweight network is deployable on low-power embedded devices to meet the requirements of the real-time applications yielding 10FPS @ 512 X 256 on NVIDIA Jetson Xavier and 15FPS @ 512 X 256 on Texas Instrument's TDA2x.

14 June 2021 in IEEE Access
Verified
Journal Article
Open access
ZAZohauddin Ahmad
Zohauddin Ahmad
YLYan-Min Liao
Yan-Min Liao
SKSheng-I Kuo
Sheng-I Kuo
You-Chia ChangYou-Chia Chang
You-Chia Chang
RCRui-Lin Chao
Rui-Lin Chao
Jin-wei ShiJin-wei Shi
Jin-wei Shi
In this work, we demonstrate the high-power and high-responsivity performance of the dual multiplication (M-) layers in In 0.52 Al 0.48 As based avalanche photodiode (APD). The dual M-layer design in our APD structure effectively constrains the multiplication process to a thin high-field region rather than the whole thick M-layer. It thus minimizes the space charge effect (SCE) within and avoids increasing the tunneling dark current for the case of directly shrinking M-layer thickness in APD. Furthermore, by combining the specially designed mesa shape with this dual M-layer structure, the edge breakdown can be well suppressed. These benefits lead to an ultra-high gain-bandwidth product (450 GHz; 1 A/W at unit gain) and a high saturation current (>12 mA) can be simultaneously achieved in our device. By nonlinearly driving a wavelength sweeping laser in the self-heterodyne lidar setup, it can generate an optical pulse train-like waveform, providing an effective optical modulation depth of 200% to feed into our demonstrated APD at the receiver-end. Under such scheme, the photo-generated RF (1 GHz) power from our APD with a 6.3 A/W responsivity can be as high as +6.95 dBm at a high (7 mA) output photocurrent. Such high-power and high-responsivity characteristics of our APD can further improve the signal-to-noise (S/N) ratio and dynamic range performances in each pixel of the lidar image. A high-quality 3-dimensional (D) FMCW lidar image is constructed based on our APD, without the integration of any electrical amplifier at the receiver end.

6 August 2021 in Sensors
Verified
Journal Article
Open access
PDF file
Tzu-Hsien SangTzu-Hsien Sang
Tzu-Hsien Sang
FCFeng-Tsun Chien
Feng-Tsun Chien
CCChia-Chih Chang
Chia-Chih Chang
Kuan-Yu TsengKuan-Yu Tseng
Kuan-Yu Tseng
BWBo-Sheng Wang
Bo-Sheng Wang
JGJiun-In Guo
Jiun-In Guo
A method of direction-of-arrival (DoA) estimation for FMCW (Frequency Modulated Continuous Wave) radar is presented. In addition to MUSIC, which is the popular high-resolution DoA estimation algorithm, deep learning has recently emerged as a very promising alternative. It is proposed in this paper to use a 3D convolutional neural network (CNN) for DoA estimation. The 3D-CNN extracts from the radar data cube spectrum features of the region of interest (RoI) centered on the potential positions of the targets, thereby capturing the spectrum phase shift information, which corresponds to DoA, along the antenna axis. Finally, the results of simulations and experiments are provided to demonstrate the superior performance, as well as the limitations, of the proposed 3D-CNN.