Merge branch 'main' into DocumentationOffline

CMakeLists.txt

@@ -46,6 +46,7 @@ find_package(Boost COMPONENTS filesystem REQUIRED)
 find_package(pcl_conversions)
 find_package(pcl_ros)
 find_package(SuiteSparse)
+find_package(TBB REQUIRED)
 
 #find_package(darknet_ros_msgs)
 #find_package(catkin REQUIRED COMPONENTS darknet_ros_msgs)
@@ -70,6 +71,7 @@ set(LIBS
         gflags
         cv_bridge
         amrl_shared_lib
+        TBB::tbb
         ${CERES_LIBRARIES}
         ${OpenCV_LIBS}
         ${PCL_LIBRARIES}

README.md

@@ -1,7 +1,7 @@
 # ObVi-SLAM
 ObVi-SLAM is a joint object-visual SLAM approach aimed at long-term multi-session robot deployments. 
 
-[[Paper](https://arxiv.org/abs/2309.15268)] [[Video](https://youtu.be/quJOgnEdaZ0)]
+[[Paper with added appendix](https://arxiv.org/abs/2309.15268)] [[Video](https://youtu.be/quJOgnEdaZ0)]
 
 Offline execution instructions coming soon. 
 ROS implementation coming late 2023/early 2024. 
@@ -12,11 +12,6 @@ Please email amanda.adkins4242@gmail.com with any questions!
 ## Evaluation
 For information on how to set up and run the comparison algorithms, see our [evaluation repo](https://github.com/ut-amrl/ObVi-SLAM-Evaluation).
 
-
-## Extended Results
-See the [version of our paper](https://drive.google.com/file/d/1Cf6QfheKa09mJO8oqgUqdTUC3y12JXRN/view?usp=share_link) with an appendix containing extended results and the full ablation study details.
-
-
 ## Installation Instructions
 <!-- TODO
 - dockerfile version (recommended)
@@ -124,10 +119,13 @@ TODO
 - Explain how to modify configuration file -- which parameters will someone need to modify for different environment, (lower priority): explain each of the parameters in the config file
 
 ## Evaluation
-Our YOLO model: TODO
+For our experiments, we used [YOLOv5](https://github.com/ut-amrl/yolov5/tree/ROS) (based on [this repo](https://github.com/ultralytics/yolov5)) with [this model](https://drive.google.com/file/d/15xv-Se991Pzes7R3KfyPBkuSQ7TeCb1T/view?usp=sharing). 
+
+We used detections with labels 'lamppost', 'treetrunk', 'bench', and 'trashcan' with [this configuration file](https://github.com/ut-amrl/ObVi-SLAM/blob/main/config/base7a_1_fallback_a_2.json). 
+
+Please contact us if you would like to obtain the videos on which we performed the evaluation. 
 
 ## TODOs
 - Add installation instructions
 - Add offline execution instructions
-- Add YOLO model -->