In recent years, active research has been conducted on computer vision and artificial intelligence (AI) for autonomous driving to increase the understanding of the importance of object detection technology using a frontal-viewing camera. However, using an RGB camera as a frontal-viewing camera can generate lens flare artifacts due to strong light sources, components of the camera lens, and foreign substances, which damage the images, making the shape of objects in the images unrecognizable. Furthermore, the object detection performance is significantly reduced owing to a lens flare during semantic segmentation performed for autonomous driving. Flare artifacts pose challenges in their removal, as they are caused by various scattering and reflection effects. The state-of-the-art methods using general scene image retain artifactual noises and fail to eliminate flare entirely when there exist severe levels of flare in the input image. In addition, no study has been conducted to solve these problems in the field of semantic segmentation for autonomous driving. Therefore, this study proposed a novel lens flare removal technique based on a class attention map-based flare removal network (CAM-FRN) and a semantic segmentation method using the images in which the lens flare is removed. CAM-FRN is a generative-based flare removal network that estimates flare regions, generates highlighted images as input, and incorporates the estimated regions into the loss function for successful artifact reconstruction and comprehensive flare removal. We synthesized a lens flare using the Cambridge-driving Labeled Video Database (CamVid) and Karlsruhe Institute of Technology and Toyota Technological Institute at Chicago (KITTI) datasets, which are road scene open datasets. The experimental results showed that semantic segmentation accuracy in images with lens flare was removed based on CAM-FRN, exhibiting 71.26% and 60.27% mean intersection over union (mIoU) in the CamVid and KITTI databases, respectively. This indicates that the proposed method is significantly better than state-of-the-art methods.

There are few studies utilizing only IR cameras for long-distance gender recognition, and they have shown low recognition performance due to their lack of color and texture information in IR images with a complex background. Therefore, a rough body segmentation-based gender recognition network (RBSG-Net) is proposed, with enhanced gender recognition performance achieved by emphasizing the silhouette of a person through a body segmentation network. Anthropometric loss for the segmentation network and an adaptive body attention module are also proposed, which effectively integrate the segmentation and classification networks. To enhance the analytic capabilities of the proposed framework, fractal dimension estimation was introduced into the system to gain insights into the complexity and irregularity of the body region, thereby predicting the accuracy of body segmentation. For experiments, near-infrared images from the Sun Yat-sen University multiple modality re-identification version 1 (SYSU-MM01) dataset and thermal images from the Dongguk body-based gender version 2 (DBGender-DB2) database were used. The equal error rates of gender recognition by the proposed model were 4.320% and 8.303% for these two databases, respectively, surpassing state-of-the-art methods.

Recently, research on the methods that use images captured during day and night times has been actively conducted in the field of person re-identification (ReID). In particular, ReID has been increasingly performed using infrared (IR) images captured at night and red-green-blue (RGB) images, in addition to ReID, which only uses RGB images captured during the daytime. However, insufficient research has been conducted on ReID that only uses IR images because their color and texture information cannot be identified easily. This study thus proposes an original and attention-guided DenseNet-based ensemble network (OADE-Net)—a ReID model that can recognize pedestrians using only IR images captured during the day and night times. The OADE-Net consists of the original and attention-guided DenseNets and a shallow convolutional neural network for the ensemble network (SCE-Net), which is a model used for combining the two models. Owing to the lack of existing open datasets that only consist of IR images, the experiments are conducted by creating a new dataset that only consists of IR images retrieved from two open databases (DBPerson-Recog-DB1 and SYSU-MM01). The experimental results of the OADE-Net showed that the achieved ReID accuracy of the DBPerson-Recog-DB1 is 79.71% in rank 1, while the mean average precision (mAP) is 78.17%. Furthermore, an accuracy of 57.30% is achieved in rank 1 in the SYSU-MM01 case, whereas the accuracy of the mAP was 41.50%. Furthermore, the accuracy of the OADE-Net in both datasets is higher than that of the existing score-level fusion and state-of-the-art methods.

Research on semantic segmentation for remote sensing road scenes advanced significantly, driven by autonomous driving technology. However, motion blur from camera or subject movements hampers segmentation performance. To address this issue, we propose a knowledge distillation-based semantic segmentation network (KDS-Net) that is robust to motion blur, eliminating the need for image restoration networks. KDS-Net leverages innovative knowledge distillation techniques and edge-enhanced segmentation loss to refine edge regions and improve segmentation precision across various receptive fields. To enhance the interpretability of segmentation quality under motion blur, we incorporate fractal dimension estimation to quantify the geometric complexity of class-specific regions, allowing for a structural assessment of predictions generated by the proposed knowledge distillation framework for autonomous driving. Experiments on well-known motion-blurred remote sensing road scene datasets (CamVid and KITTI) demonstrate mean IoU scores of 72.42% and 59.29%, respectively, surpassing state-of-the-art methods. Additionally, the lightweight KDS-Net (21.44 M parameters) enables real-time edge computing, mitigating data privacy concerns and communication overheads in internet of vehicles scenarios.