著者

Xi ZHANG Yanan ZHANG Tao GAO Yong FANG Ting CHEN

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

IEICE TRANSACTIONS on Information and Systems (ISSN:09168532)

巻号頁・発行日

vol.E106-D, no.5, pp.625-634, 2023-05-01

被引用文献数

1

---

The original single-shot multibox detector (SSD) algorithm has good detection accuracy and speed for regular object recognition. However, the SSD is not suitable for detecting small objects for two reasons: 1) the relationships among different feature layers with various scales are not considered, 2) the predicted results are solely determined by several independent feature layers. To enhance its detection capability for small objects, this study proposes an improved SSD-based algorithm called proportional channels' fusion SSD (PCF-SSD). Three enhancements are provided by this novel PCF-SSD algorithm. First, a fusion feature pyramid model is proposed by concatenating channels of certain key feature layers in a given proportion for object detection. Second, the default box sizes are adjusted properly for small object detection. Third, an improved loss function is suggested to train the above-proposed fusion model, which can further improve object detection performance. A series of experiments are conducted on the public database Pascal VOC to validate the PCF-SSD. On comparing with the original SSD algorithm, our algorithm improves the mean average precision and detection accuracy for small objects by 3.3% and 3.9%, respectively, with a detection speed of 40FPS. Furthermore, the proposed PCF-SSD can achieve a better balance of detection accuracy and efficiency than the original SSD algorithm, as demonstrated by a series of experimental results.

著者

Isana FUNAHASHI Taichi YOSHIDA Xi ZHANG Masahiro IWAHASHI

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

IEICE TRANSACTIONS on Information and Systems (ISSN:09168532)

巻号頁・発行日

vol.E105-D, no.1, pp.123-133, 2022-01-01

---

In this paper, we propose an image adjustment method for multi-exposure images based on convolutional neural networks (CNNs). We call image regions without information due to saturation and object moving in multi-exposure images lacking areas in this paper. Lacking areas cause the ghosting artifact in fused images from sets of multi-exposure images by conventional fusion methods, which tackle the artifact. To avoid this problem, the proposed method estimates the information of lacking areas via adaptive inpainting. The proposed CNN consists of three networks, warp and refinement, detection, and inpainting networks. The second and third networks detect lacking areas and estimate their pixel values, respectively. In the experiments, it is observed that a simple fusion method with the proposed method outperforms state-of-the-art fusion methods in the peak signal-to-noise ratio. Moreover, the proposed method is applied for various fusion methods as pre-processing, and results show obviously reducing artifacts.

著者

Dawei Lin Chen Wu Yiwen Jiang Yigang Li Xi Zhang Yaosheng Wang

出版者

International Research and Cooperation Association for Bio & Socio-Sciences Advancement

雑誌

BioScience Trends (ISSN:18817815)

巻号頁・発行日

pp.2021.01461, (Released:2021-12-04)

参考文献数

20

被引用文献数

2

---

It remains unknown whether and to what extend the angiotensin-converting enzyme inhibitors (ACEIs) or angiotensin receptor blockers (ARBs) can play a role in the development of atrial fibrillation (AF) after pacemaker implantation in very old patients. Therefore, we aimed to investigate the association between oral ACEIs or ARBs and the risk of developing AF in very old patients after pacemaker implantation. Patients above 80 years old with pacemaker implantation and without baseline history of AF were included and their real-world information about ACEIs or ARBs use was extracted from electronic medical records. New AF cases were confirmed via the records of outpatient visits. The multivariable Cox proportional-hazards model was used to evaluate the associations between oral ACEIs or ARBs and risk of AF after pacemaker implantation. Among a total of 388 identified patients aged 80 to 98 years, 118 used ACEIs, 174 had ARBs therapy, and 115 AF were identified after pacemaker implantation during a median follow-up time of 3.1 years. After adjustment for potential confounders, patients with daily use of ARBs had a relatively lower risk of AF after pacemaker implantation (HR: 0.627, 95% CI: 0.425, 0.926; P = 0.019) compared with those non-users, whereas ACEIs therapy didn't show a significant relation with AF risk (HR: 1.335, 95% CI: 0.894, 1.995; P = 0.157). In conclusion, for very old patients with a permanent pacemaker, daily use of oral ARBs was associated with a relative lower risk of AF after pacemaker implantation, however, daily use of ACEIs was not related with AF risk.