Liu Songtao, Zhu Yaonan, Aoyama Tadayoshi, Nakaya Masayuki, Hasegawa Yasuhisa
Department of Micro-Nano Mechanical Science and Engineering, Nagoya University, Nagoya 464-8601, Japan.
The School of Engineering, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan.
Sensors (Basel). 2024 Sep 19;24(18):6050. doi: 10.3390/s24186050.
Template matching is a common approach in bin-picking tasks. However, it often struggles in complex environments, such as those with different object poses, various background appearances, and varying lighting conditions, due to the limited feature representation of a single template. Additionally, during the bin-picking process, the template needs to be frequently updated to maintain detection performance, and finding an adaptive template from a vast dataset poses another challenge. To address these challenges, we propose a novel template searching method in a latent space trained by a Variational Auto-Encoder (VAE), which generates an adaptive template dynamically based on the current environment. The proposed method was evaluated experimentally under various conditions, and in all scenarios, it successfully completed the tasks, demonstrating its effectiveness and robustness for bin-picking applications. Furthermore, we integrated our proposed method with YOLO, and the experimental results indicate that our method effectively improves YOLO's detection performance.
模板匹配是抓取任务中的一种常用方法。然而，由于单个模板的特征表示有限，它在复杂环境中（如具有不同物体姿态、各种背景外观和不同光照条件的环境）往往会遇到困难。此外，在抓取过程中，模板需要频繁更新以保持检测性能，而从大量数据集中找到一个自适应模板是另一个挑战。为了解决这些挑战，我们提出了一种在由变分自编码器（VAE）训练的潜在空间中的新颖模板搜索方法，该方法基于当前环境动态生成自适应模板。所提出的方法在各种条件下进行了实验评估，并且在所有场景中都成功完成了任务，证明了其在抓取应用中的有效性和鲁棒性。此外，我们将所提出的方法与YOLO集成，实验结果表明我们的方法有效地提高了YOLO的检测性能。
