Applications such as Simultaneous Localization and Mapping (SLAM) can greatly benefit from RGB-D sensor data to produce 3D maps of the environment as well as sensor' s trajectory estimation. However, the resulting 3D points map can be cumbersome, and since indoor environments are mainly composed of planar surfaces, the idea is to use planes as building blocks for a SLAM process. This paper describes an RGB-D SLAM system benefiting from planes segmentation to generate lightweight 3D plane-based maps. Notre objectif est de produire des cartes 3D réduites composées uniquement de sections de plans qui peuvent être utilisées sur des plates-formes avec des ressources de mémoire et de calcul limitées. Nous présentons l'introduction des régions planaires dans un système de SLAM RGB-D régulier et évaluons les avantages en regardant la carte des deux résultats et la trajectoire estimée de la caméra.

Applications such as Simultaneous Localization and Mapping (SLAM) can greatly benefit from RGB-D sensor data to produce 3D maps of the environment as well as sensor's trajectory estimation. However, the resulting 3D points map can be cumbersome, and since indoor environments are mainly composed of planar surfaces, the idea is to use planes as building blocks for a SLAM process. This paper describes an RGB-D SLAM system benefiting from planes segmentation to generate lightweight 3D plane-based maps. Our goal is to produce reduced 3D maps composed solely of planes sections that can be used on platforms with limited memory and computation resources. We present the introduction of planar regions in a regular RGB-D SLAM system and evaluate the benefits regarding both the resulting map and estimated camera trajectory.

Applications such as Simultaneous Localization and Mapping (SLAM) can greatly benefit from RGB-D sensor data to produce 3D maps of the environment as well as sensor's trajectory estimation. However, the resulting 3D points map can be cumbersome, and since indoor environments are mainly composed of planar surfaces, the idea is to use planes as building blocks for a SLAM process. This paper describes an RGB-D SLAM system benefiting from planes segmentation to generate lightweight 3D plane-based maps. Our goal is to produce reduced 3D maps composed solely of planes sections that can be used on platforms with limited memory and computation resources. We present the introduction of planar regions in a regular RGB-D SLAM system and evaluate the benefits regarding both resulting map and estimated camera trajectory.

Applications such as Simultaneous Localization and Mapping (SLAM) can greatly benefit from RGB-D sensor data to produce 3D maps of the environment as well as sensor's trajectory estimation. However, the resulting 3D points map can be cumbersome, and since indoor environments are mainly composed of planar surfaces, the idea is to use planes as building blocks for a SLAM process. This paper describes an RGB-D SLAM system benefiting from plan segmentation to generate lightweight 3D plane-based maps. Our goal is to produce reduced 3D maps composed solely of plan sections that can be used on platforms with limited memory and computation resources. We present the introduction of planar regions in a regular RGB-D SLAM system and evaluate the benefits regarding both resulting map and estimated camera trajectory.

يمكن أن تستفيد تطبيقات مثل التوطين المتزامن ورسم الخرائط (SLAM) بشكل كبير من بيانات مستشعر RGB - D لإنتاج خرائط ثلاثية الأبعاد للبيئة بالإضافة إلى تقدير مسار المستشعر. ومع ذلك، يمكن أن تكون خريطة النقاط ثلاثية الأبعاد الناتجة مرهقة، وبما أن البيئات الداخلية تتكون أساسًا من أسطح مستوية، فإن الفكرة هي استخدام الطائرات ككتل بناء لعملية الضرب. تصف هذه الورقة نظام RGB - D SLAM الذي يستفيد من تجزئة الطائرات لتوليد خرائط مستوية ثلاثية الأبعاد خفيفة الوزن. هدفنا هو إنتاج خرائط ثلاثية الأبعاد مخفضة تتكون فقط من أقسام مستوية يمكن استخدامها على منصات ذات ذاكرة وموارد حسابية محدودة. نقدم مقدمة للمناطق المستوية في نظام RGB - D SLAM منتظم ونقيم الفوائد فيما يتعلق بكل من الخريطة الناتجة ومسار الكاميرا المقدر.