In this paper, a fast and robust infrared remote target detection network is proposed based on deep learning. Furthermore, we construct our own IR image database imitating humans in remote maritime rescue situations using FLIR M232 IR camera. First, IR image is preprocessed with contrast enhancement for data augmentation and to increase Signal-to-Noise Ratio (SNR). Second, multi-scale feature extraction is performed combined with fixed weighted kernels and convolutional neural network layers. Lastly, the feature map is mapped into a likelihood map indicating the potential locations of the targets. Experimental results reveal that the proposed method can detect remote targets even under complex backgrounds surpassing the previous methods by a significant margin of +0.62 in terms of mIOU.
In this paper, a novel 3D face recognition system utilizing the MEMS-based indirect Time-of-Flight (ToF) region-scanning LiDAR is proposed for long-distance person identification. Specifically, this face recognition system consists of two parts: (1) detection of the targeted face region by IR amplitude image and (2) 3D face recognition with the high-resolution face data of region-scanning. The proposed system is carried out on the self-collected dataset and gets maximum Rank-1 recognition rate of 95% in various distance and illumination conditions. Moreover, the proposed system outperformed the other 3D face recognition system with conventional ToF sensors in the aspect of the Rank-1 recognition rates at long distance of more than 3 meters.
This paper suggests a MEMS-based indirect time-of-flight (ToF) scanning light detection and ranging (LiDAR) system with parallel-phase demodulation. Based on the parallel-phase demodulation which extremely reduces the integration time maintaining high demodulation contrast, the proposed LiDAR can acquire accurate depth images with mean absolute error (MAE) about 1.5 cm at the distance of 1.85 m using 20 mW laser power. Meanwhile, MAE due to multipath interference (MPI) of the proposed LiDAR originally about 1.5 cm could be further reduced to less than 8 mm using support vector regression (SVR).
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.