I have tried eCognition. It is a useful tool as suggested by Mathieu. Here is the reference to one paper:
Karlson, M., Reese, H., & Ostwald, M. (2014). Tree Crown Mapping in Managed Woodlands (Parklands) of Semi-Arid West Africa Using WorldView-2 Imagery and Geographic Object Based Image Analysis. Sensors, 14(12), 22643-22669.
Also, you may want to read this:
Zagalikis, G., Cameron, A. D., & Miller, D. R. (2005). The application of digital photogrammetry and image analysis techniques to derive tree and stand characteristics. Canadian journal of forest research, 35(5), 1224-1237.
ECcognition developer. It's more flexible since it offers the possibility to program specific algorithms in the Cognition Network Language (CNL). Others examples/papers to add to those already suggested:
Object-based approach for multi-scale mangrove composition mapping using multi-resolution image datasets M Kamal, S Phinn, K Johansen - Remote Sensing, 2015 - mdpi.com
You can use ecognition and matlab.but i think ecognition is best if you are familiar. You can read the following paper ;