Visual SLAM for Dynamic Environments Based on Object Detection and Optical Flow for Dynamic Object Removal.

In dynamic indoor environments and for a Visual Simultaneous Localization and Mapping (vSLAM) system to operate, moving objects should be considered because they could affect the system's visual odometer stability and its position estimation accuracy. vSLAM can use feature points or a sequence of images, as it is the only source of input that can perform localization while simultaneously creating a map of the environment. A vSLAM system based on ORB-SLAM3 and on YOLOR was proposed in this paper. The newly proposed system in combination with an object detection model (YOLOX) applied on extracted feature points is capable of achieving 2-4% better accuracy compared to VPS-SLAM and DS-SLAM. Static feature points such as signs and benches were used to calculate the camera position, and dynamic moving objects were eliminated by using the tracking thread. A specific custom personal dataset that includes indoor and outdoor RGB-D pictures of train stations, including dynamic objects and high density of people, ground truth data, sequence data, and video recordings of the train stations and X, Y, Z data was used to validate and evaluate the proposed method. The results show that ORB-SLAM3 with YOLOR as object detection achieves 89.54% of accuracy in dynamic indoor environments compared to previous systems such as VPS-SLAM.

A combined urodynamic and electrophysiological study of diabetic cystopathy.

AIMS: The aim of this study is to compare urodynamics and electrophysiological studies in the diagnosis of diabetic cystopathy. MATERIALS AND METHODS: In this prospective study are included twenty six patients with diabetes mellitus diagnosed at least since 5 years; 17 patients with diabetes type II and 9 with type I. They were divided in two groups in respect to lower urinary tract symptoms (LUTS) and signs suggestive of lower urinary tract dysfunction (LUTD) according to the ICS standardization. Patients with LUTS/LUTD were included in Group A and patients without LUTS/LUTD in Group B. Patients underwent different studies: urodynamic, somatosensory evoked potentials (SSEP) of tibial and pudendal nerves, bulbocavernosus reflex (BCR), bulbocavernosus muscles' electromyography and motor evoked potentials after transcranial magnetic stimulation to indirectly investigate bladder's innervation. RESULTS: Abnormal urodynamics were found in 13 patients of group A (92.9%) and in 5 of group B (47.1%). This difference was statistically significant (P=0.009). Abnormally prolonged latency of P40 of tibial SSEP was found in 11 patients of group A (78.6%) and in 4 of group B (33.3%) and this difference was also statistically significant (P=0.04). Differences between the two groups concerning: i) peripheral polyneuropathy; ii) pudendal SSEP, iii) dysfunction of central nervous system and iv) abnormal BCR were not statistically significant. CONCLUSION: The study of tibial SSEP is an easily performed test and it is well correlated to abnormal urodynamics in diabetic patients with and without LUTD/LUTS.

Urodynamics prior to renal transplantation--its impact on treatment decision and final results.

OBJECTIVE: To evaluate the role of urodynamics prior to renal transplantation in a selected group of patients. MATERIAL AND METHODS: This retrospective study included 44 consecutive patients (20 males, 24 females; age range 7-57 years; mean age 27.14 +/- 15.17 years) referred for urodynamic evaluation due to known or suspected lower urinary tract dysfunction. End-stage renal disease was due to obstructive uropathy in nine patients, reflux nephropathy in 13, neuropathic bladder in nine and various parenchymal diseases in four; in nine patients the origin of renal failure remained obscure despite detailed investigations. All the patients were subjected to detailed video-urodynamics. RESULTS: In 30 patients (68.2%) a urodynamic abnormality was found which precluded kidney transplantation into their native bladders without major reconstruction, a minor corrective procedure and/or pharmacotherapy prior to transplantation. More specifically, seven patients were found to have infravesical obstruction, one had a small fibrotic bladder, seven had small capacity bladders due to long-term non-use, four were found on cystometry to have an idiopathic overactive detrusor and 11 exhibited evidence of neurogenic lower urinary tract dysfunction. Fourteen affected patients (32%) were subjected to treatment prior to kidney transplantation: three underwent bladder neck incision, seven recycling of their small bladders, one substitution and three augmentation cystoplasty. Kidney transplantation followed reconstruction 3-18 months later (mean 5 +/- 6.2 months). The follow-up ranged from 12 to 107 months (mean 25 +/- 21 months). CONCLUSION: Urodynamics prior to kidney transplantation in this selected group of patients established a definitive diagnosis of the type of lower urinary tract dysfunction, offered the opportunity for reconstructive surgery and enabled kidney transplantation.