Update README.md

README.md

@@ -54,6 +54,11 @@ according to the number of occupied pixels in the annotated
 bounding box. Experiments show that Faster R-CNN with
 ResNet101 as feature extractor outperforms the other algorithms.
 
+
+![Image description](fig5.jpg)
+
+Fig. 5. The proposed (a) Color-based (b) Sparse LiDAR-based (c) Dense LiDAR-based and (d) Color and dense LiDAR based frameworks.
+
 # An Efficient Multi-sensor Fusion Approach for Object Detection in Maritime Environmentt [6]: 
 Robust real-time object detection and tracking are
 challenging problems in autonomous transportation systems
@@ -77,7 +82,7 @@ results in maritime environments.
 
 ![Image description](figure4.jpg)
 
-Fig. 4. Mapping the detected objects by all sensors on (a) radar coordinates and (b) RGB camera image. ’F’ box in the bottom left corner of
+Fig. 5. Mapping the detected objects by all sensors on (a) radar coordinates and (b) RGB camera image. ’F’ box in the bottom left corner of
 each figure indicates the location of the ferry.