在恶劣的天气条件下,DSF-YOLO提供了可靠的多尺度交通信号检测
Jun Li1, QinWen Deng1, WenXin Gao1
1College of Information Engineering, Sichuan Agricultural University, Ya'an, 625000, SiChuan Province, China.
Scientific reports
|July 8, 2025
概括
本研究介绍了一种改进的交通标志识别 (TSR) 模型,使用基于注意力的特征金字塔和动态卷曲. 改进后的模型在恶劣天气条件下实现了小型交通标志的更高准确性.
科学领域:
- 计算机视觉 计算机视觉
- 机器学习 机器学习
- 自主驾驶系统 自主驾驶系统
背景情况:
- 交通标志识别 (TSR) 对于自动驾驶至关重要.
- 当前的TSR方法与复杂的天气条件作斗争,影响准确性.
- 在不利的环境中,发现小型交通标志实例尤其具有挑战性.
研究的目的:
- 开发一个强大的TSR模型,能够在复杂的天气条件下准确识别交通标志.
- 为了提高在恶劣天气中检测小型交通标志的实例.
- 提高TSR系统的整体性能和通用化能力.
主要方法:
- 使用基于注意力的动态序列融合特征金字塔来提高识别精度.
- 集成了动态蛇形卷积和Wise-IoU,以捕捉精细的特征并减轻低质量的实例.
- 一个新的数据增强库 (Albumentations) 模拟了复杂的天气,并使用TIDE进行性能评估.
主要成果:
- 该模型在多个数据集的平均平均精度 (mAP) 中取得了显著的改进:在TT-100K上为9%,在GTSDB上为1.5%,在BDD100K上为2.6%.
- 与基线相比,分类 (Cls) 和局部化 (Loc) 的指标略有下降.
- 该模型在复杂的天气条件下检测小目标时表现出了出色的概括性和稳定性.
结论:
- 提出的基于注意力的动态特征金字塔模型显著提高了在恶劣天气中的交通标志识别.
- 集成动态卷曲和先进的 IoU 改进了小型和低质量的交通标志的检测.
- 该模型显示了现实世界自动驾驶应用的巨大潜力,需要可靠的TSR.
相关概念视频
Masonry in Cold and Hot Weather Conditions
137
In cold weather, masonry construction requires specific precautions to ensure mortar does not freeze before curing, as this can significantly weaken its strength and watertightness. Mortar temperature should be maintained between 60°F and 80°F to support proper hydration and curing. Below 40°F, mortar water must be heated, but should not exceed 120°F as high temperatures can reduce mortar's compressive and bond strength.
Other key practices include keeping masonry units...
Other key practices include keeping masonry units...
137
Sight Distance in a Vertical Curve
135
Sight distance on vertical curves is critical in roadway design. It ensures drivers can see far enough ahead to identify and respond to hazards effectively. This directly impacts safety, driver comfort, and the overall efficiency of the transportation network.Vertical curves are classified into crest and sag curves based on their geometry. For crest curves, sight distance is determined by the line of sight between a driver's eye and a small object on the road's surface. Design parameters for...
135
Difference from Background: Limit of Detection
7.1K
The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...
The LOD indicates the presence or absence...
7.1K
Precipitation and Co-precipitation
2.1K
Precipitation and coprecipitation methods can be used to separate a mixture of ions in a solution. In qualitative inorganic analysis, ions that form sparingly soluble precipitates with the same reagent are separated based on the differences in solubility products. For example, consider the separation of Cu(II) and Fe(II) ions by precipitation as insoluble sulfides. First, copper(II) sulfide is precipitated by the addition of acidic H2S, where the dissociation of H2S is suppressed. Adding H2S...
2.1K
Precipitation Gravimetry
7.6K
Precipitation gravimetry is based on converting an analyte into a sparingly soluble precipitate, which is separated by filtration and weighed. An ideal precipitate should be pure, insoluble, of known composition, and easily filtered from the reaction mixture.
In determining nickel by gravimetric analysis, a precipitant of ethanolic dimethylglyoxime is added to a hot nickel salt solution. This is quickly followed by the dropwise addition of dilute ammonia solution until precipitation occurs. A...
In determining nickel by gravimetric analysis, a precipitant of ethanolic dimethylglyoxime is added to a hot nickel salt solution. This is quickly followed by the dropwise addition of dilute ammonia solution until precipitation occurs. A...
7.6K
Uniform Depth Channel Flow: Problem Solving
130
To calculate the flow rate for a trapezoidal channel, first, identify the bottom width, side slope, and flow depth of the channel. The cross-sectional area (A) corresponding to the depth of flow (y), channel bottom width (B), and side slope (θ) is determined by:Next, calculate the wetted perimeter, which includes the bottom width and the sloped side lengths in contact with the water. Using the values of the cross-sectional area and the wetted perimeter, determine the hydraulic radius by...
130


