论文标题
在人口稠密的发展中心中的自动招牌检测和本地化
Automatic Signboard Detection and Localization in Densely Populated Developing Cities
论文作者
论文摘要
由于缺乏自动注释系统，大多数发展城市的城市机构在数字上都是未标记的。因此，在此类城市中，位置和轨迹服务（例如Google Maps，Uber等）仍未得到充分利用。自然场景图像中的准确招牌检测是从此类城市街道检索无错误的信息的最重要任务。然而，开发准确的招牌本地化系统仍然是尚未解决的挑战，因为它的外观包括文本图像和令人困惑的背景。我们提出了一种新型的对象检测方法，该方法可以自动检测招牌，适合此类城市。我们通过结合两种专门的预处理方法和一种运行时效高参数值选择算法来使用更快的基于R-CNN的定位。我们采用了一种增量方法，通过使用我们构建的SVSO（Street View Signboard对象）招牌数据集，通过详细的评估和基线进行详细评估和比较，其中包含六个发展中国家的自然场景图像。我们在SVSO数据集和Open Image数据集上演示了我们提出的方法的最新性能。我们提出的方法可以准确地检测招牌（即使图像包含多种形状和颜色的多个嘈杂背景的招牌）在SVSO独立测试集上达到0.90 MAP（平均平均精度）得分。我们的实施可在以下网址获得：https：//github.com/sadrultoaha/signboard-detection
Most city establishments of developing cities are digitally unlabeled because of the lack of automatic annotation systems. Hence location and trajectory services such as Google Maps, Uber etc remain underutilized in such cities. Accurate signboard detection in natural scene images is the foremost task for error-free information retrieval from such city streets. Yet, developing accurate signboard localization system is still an unresolved challenge because of its diverse appearances that include textual images and perplexing backgrounds. We present a novel object detection approach that can detect signboards automatically and is suitable for such cities. We use Faster R-CNN based localization by incorporating two specialized pretraining methods and a run time efficient hyperparameter value selection algorithm. We have taken an incremental approach in reaching our final proposed method through detailed evaluation and comparison with baselines using our constructed SVSO (Street View Signboard Objects) signboard dataset containing signboard natural scene images of six developing countries. We demonstrate state-of-the-art performance of our proposed method on both SVSO dataset and Open Image Dataset. Our proposed method can detect signboards accurately (even if the images contain multiple signboards with diverse shapes and colours in a noisy background) achieving 0.90 mAP (mean average precision) score on SVSO independent test set. Our implementation is available at: https://github.com/sadrultoaha/Signboard-Detection
