• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Intelligent robots and computer vision XXXI: algorithms and techniques >Real-time, resource-constrained object classification on a micro-air vehicle
【24h】

Real-time, resource-constrained object classification on a micro-air vehicle

机译：微型飞机上资源受限的实时对象分类

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

A real-time embedded object classification algorithm is developed through the novel combination of binary feature descriptors, a bag-of-visual-words object model and the cortico-striatal loop (CSL) learning algorithm. The BRIEF, ORB and FREAK binary descriptors are tested and compared to SIFT descriptors with regard to their respective classification accuracies, execution times, and memory requirements when used with CSL on a 12.6 g ARM Cortex embedded processor running at 800 MHz. Additionally, the effect of χ~2 feature mapping and opponent-color representations used with these descriptors is examined. These tests are performed on four data sets of varying sizes and difficulty, and the BRIEF descriptor is found to yield the best combination of speed and classification accuracy. Its use with CSL achieves accuracies between 67% and 95% of those achieved with SIFT descriptors and allows for the embedded classification of a 128×192 pixel image in 0.15 seconds, 60 times faster than classification with SIFT. χ~2 mapping is found to provide substantial improvements in classification accuracy for all of the descriptors at little cost, while opponent-color descriptors are offer accuracy improvements only on colorful datasets.
机译：通过将二进制特征描述符，视觉词袋对象模型和皮质-纹状体环（CSL）学习算法进行新颖的组合，开发了一种实时嵌入式对象分类算法。在以800 MHz运行的12.6 g ARM Cortex嵌入式处理器上与CSL一起使用时，将测试Brief，ORB和FREAK二进制描述符并将它们与SIFT描述符进行比较，以了解它们各自的分类精度，执行时间和内存要求。此外，还检查了这些描述符使用的χ〜2特征映射和对手颜色表示的效果。这些测试是在四个大小和难度不同的数据集上执行的，并且发现Brief描述符可产生速度和分类精度的最佳组合。与CSL配合使用时，其精度达到了SIFT描述符的67％至95％，并且可以在0.15秒内对128×192像素图像进行嵌入式分类，比SIFT的分类速度快60倍。发现χ〜2映射可以以很少的成本为所有描述符提供实质性的分类改进，而对手颜色的描述符仅在彩色数据集上提供准确性改进。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号