Detecting and classifying real-life small traffic signs from large input images is difficult due to their occupying fewer pixels relative to larger targets. To address this challenge, we proposed a deep-learning-based model (Dense-RefineDet) that applies a single-shot, object-detection framework (RefineDet) to maintain a suitable accuracy–speed trade-off. We constructed a dense connection-related transfer-connection block to combine high-level feature layers with low-level feature layers to optimize the use of the higher layers to obtain additional contextual information. Additionally, we presented an anchor-design method to provide suitable anchors for detecting small traffic signs. Experiments using the Tsinghua-Tencent 100K dataset demonstrated that Dense-RefineDet achieved competitive accuracy at high-speed detection (0.13 s/frame) of small-, medium-, and large-scale traffic signs (recall: 84.3%, 95.2%, and 92.6%; precision: 83.9%, 95.6%, and 94.0%). Moreover, experiments using the Caltech pedestrian dataset indicated that the miss rate of Dense-RefineDet was 54.03% (pedestrian height > 20 pixels), which outperformed other state-of-the-art methods.
展开▼
机译:由于它们占据了较大目标的占用较少的像素,检测和分类来自大输入图像的真实寿命的小流量标志很难。为了解决这一挑战,我们提出了一种基于深度学习的模型(密集摘断),适用一次射击,对象检测框架(RefinteTet)来维持合适的精度速度折衷。我们构建了密集的连接相关的传输连接块,以将高级特征层与低电平特征层组合,以优化使用较高层以获得其他上下文信息。此外,我们介绍了一种锚设计方法,以提供用于检测小交通标志的合适锚点。使用清华腾讯100K数据集的实验表明,致密的摘断在小型,中型和大型交通标志的高速检测(0.13 S /框架)下实现了竞争准确性(召回:84.3%,95.2%,和92.6%;精确:83.9%,95.6%和94.0%)。此外,使用CALTECH行人数据集的实验表明,密集摘断的错过率为54.03%(行人高度> 20像素),这效果优于其他最先进的方法。
展开▼