Rapid advances in deep learning for computer vision have driven the adoption of RGB camera-based adaptive traffic light systems. These systems improve traffic safety and pedestrian comfort. However, they often overlook the needs of people with mobility restrictions. Moreover, RGB camera–based detection is vulnerable to adverse weather and raises privacy concerns. To address these issues, we propose a fully automated traffic light system based on thermal detectors. It dynamically adjusts signal durations for individuals with walking impairments or mobility burden. It also triggers auditory signals for visually impaired individuals. Together, these features help create barrier-free intersections for all users. To this end, we build a thermal dataset for people with mobility restrictions (TD4PWMR). It captures diverse pedestrian scenarios, particularly focusing on individuals with mobility aids or mobility burdens. It includes various environmental conditions, such as different lighting, weather, and crowded urban settings. While thermal imaging offers advantages in terms of privacy and robustness to adverse conditions, it also presents challenges for object detection. Thermal images lack color and fine texture details. They also typically have lower resolution than RGB images. To overcome these limitations, we develop YOLO-Thermal, a novel variant of the YOLO architecture. It integrates advanced feature extraction and attention mechanisms. These improvements enhance detection accuracy and robustness in thermal imaging. Experiments demonstrate that the proposed thermal detector outperforms existing detectors, while the proposed traffic light system effectively enhances barrier-free intersections. The source codes and dataset are available at https://github.com/leon2014dresden/YOLO-THERMAL.
ABSTRACT Unreduced gametes naturally promote polyploidization and are valuable in breeding polyploid offspring. Bigleaf hydrangea ( Hydrangea macrophylla ssp. macrophylla ), a major ornamental crop, has shown spontaneous polyploidization rates ranging from 0% to 94% in previous crosses. These rates depended on the male parent and indicated unreduced pollen formation. To identify cultivars producing unreduced pollen and assess the variation and stability of this trait, we determined the 2C and pollen DNA content from 81 cultivars using flow cytometry. Diploid and triploid cultivars were identified that produced exclusively unreduced pollen, whereas others produced a mixture of unreduced and reduced pollen in varying proportions or exclusively reduced pollen. Flow cytometry of pollen samples collected over multiple years, combined with offspring analyses from repeated crosses, confirmed the consistent production of cultivar‐specific pollen qualities, indicating strong genetic control. Thus, cultivars producing pollen with one, two or—in the case of triploids—three or aneuploid chromosome sets were identified, providing a basis for targeted polyploid breeding. Additionally, we provide pollen data of five H. macrophylla ssp. serrata and four H. paniculata cultivars.
The roles of light and carbohydrates in adventitious root formation of Hydrangea macrophylla cuttings of the cultivars 'Caipirinha' and 'Clarissa' were investigated. Cuttings were planted immediately or dark-stored for seven days prior to cultivation under light. The leaf and rooting phenotype, relative chlorophyll content, carbohydrate levels in different cutting sections and rooting response to hexose were analyzed. Surprisingly, pronounced leaf yellowing and reddening and a strong hexose accumulation in the cutting leaves indicated that the hydrangea cuttings experienced light stress under a photosynthetic photon flux density (PPFD) of 100 µmol m-2 s-1. Reduction in PPFD to 50 µmol m-2 s-1 decreased these symptoms and increased chlorophyll content, but impaired rooting. The effects of dark storage depended on cultivar, PPFD, and hydration of cuttings. 'Clarissa' exhibited lower rooting success, particularly after dark storage and low light, and showed lower hexose-to-sucrose ratios and hexose concentrations in the stem base than 'Caipirinha'. Rooting of 'Clarissa' could not be rescued by sugar supplementation, whereas application of 27 mM glucose plus 30 mM fructose for 24 h before planting enhanced rooting of 'Caipirinha'. The lower hexose level in the stem base of 'Clarissa' does not appear to be the critical factor underlying its low rooting capacity.
